['--alg', 'sac', '--env', 'Walker2d-v3', '--learn', 'brac', '--traj', 'medium', '--seed', '0', '--data', '100000']
1528.6775868130853
episode: 0 training return: tensor(-445919.5938, device='cuda:0')
episode: 1 training return: tensor(-1.6139e+10, device='cuda:0')
episode: 2 training return: tensor(-1.0425e+11, device='cuda:0')
episode: 3 training return: tensor(-4.9095e+10, device='cuda:0')
epoch: 1 test_true_pfm: 112.16022581876443
episode: 4 training return: tensor(-2.3411e+09, device='cuda:0')
episode: 5 training return: tensor(-5.7411e+09, device='cuda:0')
episode: 6 training return: tensor(-1.9017e+10, device='cuda:0')
episode: 7 training return: tensor(-6.4003e+09, device='cuda:0')
epoch: 2 test_true_pfm: 130.97590398617533
episode: 8 training return: tensor(-334289.9688, device='cuda:0')
episode: 9 training return: tensor(-5.2885e+09, device='cuda:0')
episode: 10 training return: tensor(-90038.3047, device='cuda:0')
episode: 11 training return: tensor(-689610.1250, device='cuda:0')
epoch: 3 test_true_pfm: -93.96592959396743
episode: 12 training return: tensor(-862954.0625, device='cuda:0')
episode: 13 training return: tensor(-575430.7500, device='cuda:0')
episode: 14 training return: tensor(-23099.8457, device='cuda:0')
episode: 15 training return: tensor(-19964.5039, device='cuda:0')
epoch: 4 test_true_pfm: 107.28163792503192
episode: 16 training return: tensor(-24089.7480, device='cuda:0')
episode: 17 training return: tensor(-18525.0781, device='cuda:0')
episode: 18 training return: tensor(-2039063.7500, device='cuda:0')
episode: 19 training return: tensor(-19858.9902, device='cuda:0')
epoch: 5 test_true_pfm: 103.32593662498259
episode: 20 training return: tensor(-12310.3330, device='cuda:0')
episode: 21 training return: tensor(-23014.6367, device='cuda:0')
episode: 22 training return: tensor(-59601.7578, device='cuda:0')
episode: 23 training return: tensor(-1613189.7500, device='cuda:0')
epoch: 6 test_true_pfm: 91.00931256332417
episode: 24 training return: tensor(-17704.4355, device='cuda:0')
episode: 25 training return: tensor(-19783.9531, device='cuda:0')
episode: 26 training return: tensor(-11894.4541, device='cuda:0')
episode: 27 training return: tensor(-15569.2109, device='cuda:0')
epoch: 7 test_true_pfm: 103.17073136213924
episode: 28 training return: tensor(-17083.7988, device='cuda:0')
episode: 29 training return: tensor(-892302.0625, device='cuda:0')
episode: 30 training return: tensor(-901053.4375, device='cuda:0')
episode: 31 training return: tensor(-778553.1250, device='cuda:0')
epoch: 8 test_true_pfm: 26.791204564741154
episode: 32 training return: tensor(-14769.0371, device='cuda:0')
episode: 33 training return: tensor(-16065.1572, device='cuda:0')
episode: 34 training return: tensor(-2590947., device='cuda:0')
episode: 35 training return: tensor(-723161.1875, device='cuda:0')
epoch: 9 test_true_pfm: -47.11181165723525
episode: 36 training return: tensor(-1142930.6250, device='cuda:0')
episode: 37 training return: tensor(-26867.3984, device='cuda:0')
episode: 38 training return: tensor(-503163.0938, device='cuda:0')
episode: 39 training return: tensor(-2578248.5000, device='cuda:0')
epoch: 10 test_true_pfm: -118.68444459685715
episode: 40 training return: tensor(-1183279.7500, device='cuda:0')
episode: 41 training return: tensor(-326547.8125, device='cuda:0')
episode: 42 training return: tensor(-463726.8750, device='cuda:0')
episode: 43 training return: tensor(-49107032., device='cuda:0')
epoch: 11 test_true_pfm: -84.72140457831436
episode: 44 training return: tensor(-203438.2031, device='cuda:0')
episode: 45 training return: tensor(-500422.2812, device='cuda:0')
episode: 46 training return: tensor(-629154.1250, device='cuda:0')
episode: 47 training return: tensor(-678510.9375, device='cuda:0')
epoch: 12 test_true_pfm: 3.771109619997721
episode: 48 training return: tensor(-1153660.7500, device='cuda:0')
episode: 49 training return: tensor(-252241.7031, device='cuda:0')
episode: 50 training return: tensor(-649087.3750, device='cuda:0')
episode: 51 training return: tensor(-17031.3633, device='cuda:0')
epoch: 13 test_true_pfm: 6.200035669454965
episode: 52 training return: tensor(-27820.1699, device='cuda:0')
episode: 53 training return: tensor(-2076147.5000, device='cuda:0')
episode: 54 training return: tensor(-1161302.6250, device='cuda:0')
episode: 55 training return: tensor(-16712.5039, device='cuda:0')
epoch: 14 test_true_pfm: 0.33252673666315086
episode: 56 training return: tensor(-200515.3750, device='cuda:0')
episode: 57 training return: tensor(-30631.9023, device='cuda:0')
episode: 58 training return: tensor(-12067355., device='cuda:0')
episode: 59 training return: tensor(-24387.4902, device='cuda:0')
epoch: 15 test_true_pfm: -10.383040062170041
episode: 60 training return: tensor(-30725.5957, device='cuda:0')
episode: 61 training return: tensor(-28602.4766, device='cuda:0')
episode: 62 training return: tensor(-13544.6436, device='cuda:0')
episode: 63 training return: tensor(-8161.7900, device='cuda:0')
epoch: 16 test_true_pfm: 0.6316817431335645
episode: 64 training return: tensor(-12393.1357, device='cuda:0')
episode: 65 training return: tensor(-538070.3125, device='cuda:0')
episode: 66 training return: tensor(-13689.0859, device='cuda:0')
episode: 67 training return: tensor(-396622.3750, device='cuda:0')
epoch: 17 test_true_pfm: -23.914341782568144
episode: 68 training return: tensor(-507192.0625, device='cuda:0')
episode: 69 training return: tensor(-16434.9727, device='cuda:0')
episode: 70 training return: tensor(-10416.9756, device='cuda:0')
episode: 71 training return: tensor(-280620.7500, device='cuda:0')
epoch: 18 test_true_pfm: -3.1652393472056795
episode: 72 training return: tensor(-363035.7500, device='cuda:0')
episode: 73 training return: tensor(-517144.6875, device='cuda:0')
episode: 74 training return: tensor(-11807.8086, device='cuda:0')
episode: 75 training return: tensor(-29191.0723, device='cuda:0')
epoch: 19 test_true_pfm: -60.53203896873771
episode: 76 training return: tensor(-10878.0420, device='cuda:0')
episode: 77 training return: tensor(-22726018., device='cuda:0')
episode: 78 training return: tensor(-9928.7393, device='cuda:0')
episode: 79 training return: tensor(-10447.9082, device='cuda:0')
epoch: 20 test_true_pfm: 32.38861066801696
episode: 80 training return: tensor(-9639.1025, device='cuda:0')
episode: 81 training return: tensor(-12216.1562, device='cuda:0')
episode: 82 training return: tensor(-483302.7812, device='cuda:0')
episode: 83 training return: tensor(-8519547., device='cuda:0')
epoch: 21 test_true_pfm: -79.86751832252784
episode: 84 training return: tensor(-638642.1875, device='cuda:0')
episode: 85 training return: tensor(-9726.0322, device='cuda:0')
episode: 86 training return: tensor(-9771.3848, device='cuda:0')
episode: 87 training return: tensor(-13000.1279, device='cuda:0')
epoch: 22 test_true_pfm: 87.27571423882523
episode: 88 training return: tensor(-20471.3633, device='cuda:0')
episode: 89 training return: tensor(-18522.9141, device='cuda:0')
episode: 90 training return: tensor(-16795.9941, device='cuda:0')
episode: 91 training return: tensor(-11211.7627, device='cuda:0')
epoch: 23 test_true_pfm: -26.06486464576683
episode: 92 training return: tensor(-12575.5439, device='cuda:0')
episode: 93 training return: tensor(-10465.1348, device='cuda:0')
episode: 94 training return: tensor(-9876.3359, device='cuda:0')
episode: 95 training return: tensor(-113350.1641, device='cuda:0')
epoch: 24 test_true_pfm: -8.251129726459398
episode: 96 training return: tensor(-12187.9365, device='cuda:0')
episode: 97 training return: tensor(-9482.5771, device='cuda:0')
episode: 98 training return: tensor(-15605.4297, device='cuda:0')
episode: 99 training return: tensor(-9039.0352, device='cuda:0')
epoch: 25 test_true_pfm: -5.428710906770998
episode: 100 training return: tensor(-11515.1338, device='cuda:0')
episode: 101 training return: tensor(-13024.5957, device='cuda:0')
episode: 102 training return: tensor(-10313.8486, device='cuda:0')
episode: 103 training return: tensor(-9950.5537, device='cuda:0')
epoch: 26 test_true_pfm: -85.15247676185317
episode: 104 training return: tensor(-14871.6572, device='cuda:0')
episode: 105 training return: tensor(-18536.3027, device='cuda:0')
episode: 106 training return: tensor(-58888.0469, device='cuda:0')
episode: 107 training return: tensor(-30306.3770, device='cuda:0')
epoch: 27 test_true_pfm: 6.543517442285999
episode: 108 training return: tensor(-26928.8496, device='cuda:0')
episode: 109 training return: tensor(-36384.4531, device='cuda:0')
episode: 110 training return: tensor(-19405.7930, device='cuda:0')
episode: 111 training return: tensor(-17086.7656, device='cuda:0')
epoch: 28 test_true_pfm: -107.3861127155796
episode: 112 training return: tensor(-17573.4883, device='cuda:0')
episode: 113 training return: tensor(-31175.3379, device='cuda:0')
episode: 114 training return: tensor(-16575.6328, device='cuda:0')
episode: 115 training return: tensor(-25706.5059, device='cuda:0')
epoch: 29 test_true_pfm: 56.11916019631479
episode: 116 training return: tensor(-42710.9414, device='cuda:0')
episode: 117 training return: tensor(-24890.7227, device='cuda:0')
episode: 118 training return: tensor(-18932.3633, device='cuda:0')
episode: 119 training return: tensor(-18995.8184, device='cuda:0')
epoch: 30 test_true_pfm: 158.86730614693008
episode: 120 training return: tensor(-20134.4961, device='cuda:0')
episode: 121 training return: tensor(-15499.8584, device='cuda:0')
episode: 122 training return: tensor(-99708.8047, device='cuda:0')
episode: 123 training return: tensor(-25372.0254, device='cuda:0')
epoch: 31 test_true_pfm: -94.57511327427623
episode: 124 training return: tensor(-21545.1250, device='cuda:0')
episode: 125 training return: tensor(-15330.4326, device='cuda:0')
episode: 126 training return: tensor(-17582.3027, device='cuda:0')
episode: 127 training return: tensor(-25932.8203, device='cuda:0')
epoch: 32 test_true_pfm: -8.442031864796052
episode: 128 training return: tensor(-32260.8750, device='cuda:0')
episode: 129 training return: tensor(-57234.6016, device='cuda:0')
episode: 130 training return: tensor(-78539.1250, device='cuda:0')
episode: 131 training return: tensor(-12103.7129, device='cuda:0')
epoch: 33 test_true_pfm: -84.2630787710715
episode: 132 training return: tensor(-59254.9570, device='cuda:0')
episode: 133 training return: tensor(-36525.7070, device='cuda:0')
episode: 134 training return: tensor(-13543.5859, device='cuda:0')
episode: 135 training return: tensor(-18952.5820, device='cuda:0')
epoch: 34 test_true_pfm: -12.14597460435643
episode: 136 training return: tensor(-60864.9531, device='cuda:0')
episode: 137 training return: tensor(-509779.4062, device='cuda:0')
episode: 138 training return: tensor(-90037.5000, device='cuda:0')
episode: 139 training return: tensor(-166364.6875, device='cuda:0')
epoch: 35 test_true_pfm: 98.46577527011765
episode: 140 training return: tensor(-42359.2266, device='cuda:0')
episode: 141 training return: tensor(-24729.7559, device='cuda:0')
episode: 142 training return: tensor(-69789.7891, device='cuda:0')
episode: 143 training return: tensor(-96136.3594, device='cuda:0')
epoch: 36 test_true_pfm: 94.63794387889722
episode: 144 training return: tensor(-31473.4297, device='cuda:0')
episode: 145 training return: tensor(-15531.0342, device='cuda:0')
episode: 146 training return: tensor(-54760.8672, device='cuda:0')
episode: 147 training return: tensor(-485443.2188, device='cuda:0')
epoch: 37 test_true_pfm: 39.66727933178293
episode: 148 training return: tensor(-48938360., device='cuda:0')
episode: 149 training return: tensor(-2.9094e+08, device='cuda:0')
episode: 150 training return: tensor(-4.2057e+08, device='cuda:0')
episode: 151 training return: tensor(-38495.5117, device='cuda:0')
epoch: 38 test_true_pfm: 34.3710226438024
episode: 152 training return: tensor(-27441.0195, device='cuda:0')
episode: 153 training return: tensor(-9.9595e+08, device='cuda:0')
episode: 154 training return: tensor(-611167.6875, device='cuda:0')
episode: 155 training return: tensor(-40183.8672, device='cuda:0')
epoch: 39 test_true_pfm: -4.945491764749415
episode: 156 training return: tensor(-5.9650e+08, device='cuda:0')
episode: 157 training return: tensor(-1662450.6250, device='cuda:0')
episode: 158 training return: tensor(-1.4124e+08, device='cuda:0')
episode: 159 training return: tensor(-3196999.5000, device='cuda:0')
epoch: 40 test_true_pfm: -25.502796571735903
episode: 160 training return: tensor(-78036128., device='cuda:0')
episode: 161 training return: tensor(-3936468.2500, device='cuda:0')
episode: 162 training return: tensor(-5252089., device='cuda:0')
episode: 163 training return: tensor(-3.9497e+09, device='cuda:0')
epoch: 41 test_true_pfm: -278.7845844925051
episode: 164 training return: tensor(-1.4299e+08, device='cuda:0')
episode: 165 training return: tensor(-62728.8047, device='cuda:0')
episode: 166 training return: tensor(-39484.8086, device='cuda:0')
episode: 167 training return: tensor(-13168.0039, device='cuda:0')
epoch: 42 test_true_pfm: 34.89573924608894
episode: 168 training return: tensor(-12444.0791, device='cuda:0')
episode: 169 training return: tensor(-21308.9629, device='cuda:0')
episode: 170 training return: tensor(-10110.6367, device='cuda:0')
episode: 171 training return: tensor(-1295534.1250, device='cuda:0')
epoch: 43 test_true_pfm: 64.40972507954625
episode: 172 training return: tensor(-12676.0391, device='cuda:0')
episode: 173 training return: tensor(-12284.5439, device='cuda:0')
episode: 174 training return: tensor(-12240.6670, device='cuda:0')
episode: 175 training return: tensor(-12291.1709, device='cuda:0')
epoch: 44 test_true_pfm: 62.649123697520174
episode: 176 training return: tensor(-11982.2588, device='cuda:0')
episode: 177 training return: tensor(-12349.5156, device='cuda:0')
episode: 178 training return: tensor(-12440.9775, device='cuda:0')
episode: 179 training return: tensor(-76491.2656, device='cuda:0')
epoch: 45 test_true_pfm: -10.632010890858803
episode: 180 training return: tensor(-6691.7861, device='cuda:0')
episode: 181 training return: tensor(-117777.8828, device='cuda:0')
episode: 182 training return: tensor(-6926.1938, device='cuda:0')
episode: 183 training return: tensor(-43217.1992, device='cuda:0')
epoch: 46 test_true_pfm: 347.9799367087492
episode: 184 training return: tensor(-69509.7578, device='cuda:0')
episode: 185 training return: tensor(-1066321.3750, device='cuda:0')
episode: 186 training return: tensor(-4984610.5000, device='cuda:0')
episode: 187 training return: tensor(-1932616.7500, device='cuda:0')
epoch: 47 test_true_pfm: 323.40978455711365
episode: 188 training return: tensor(-21797.0430, device='cuda:0')
episode: 189 training return: tensor(-1729515., device='cuda:0')
episode: 190 training return: tensor(-228148.6250, device='cuda:0')
episode: 191 training return: tensor(-28484.5586, device='cuda:0')
epoch: 48 test_true_pfm: 38.38252424828638
episode: 192 training return: tensor(-25902.5078, device='cuda:0')
episode: 193 training return: tensor(-6362.1333, device='cuda:0')
episode: 194 training return: tensor(-15144.1543, device='cuda:0')
episode: 195 training return: tensor(-23435.2129, device='cuda:0')
epoch: 49 test_true_pfm: -57.44674434459676
episode: 196 training return: tensor(-42982.5547, device='cuda:0')
episode: 197 training return: tensor(-104910.0156, device='cuda:0')
episode: 198 training return: tensor(-10658.3926, device='cuda:0')
episode: 199 training return: tensor(-10890.4600, device='cuda:0')
epoch: 50 test_true_pfm: 27.471782825307017
episode: 200 training return: tensor(-10334.9561, device='cuda:0')
episode: 201 training return: tensor(-8000.5718, device='cuda:0')
episode: 202 training return: tensor(-6179.7690, device='cuda:0')
episode: 203 training return: tensor(-6236.2412, device='cuda:0')
epoch: 51 test_true_pfm: -30.59744169133424
episode: 204 training return: tensor(-8112.5054, device='cuda:0')
episode: 205 training return: tensor(-7655.6831, device='cuda:0')
episode: 206 training return: tensor(-5771.3110, device='cuda:0')
episode: 207 training return: tensor(-7510.5371, device='cuda:0')
epoch: 52 test_true_pfm: -39.73225292375553
episode: 208 training return: tensor(-42819.1406, device='cuda:0')
episode: 209 training return: tensor(-7003.7544, device='cuda:0')
episode: 210 training return: tensor(-204036.9062, device='cuda:0')
episode: 211 training return: tensor(-7047.1328, device='cuda:0')
epoch: 53 test_true_pfm: -13.712290261342185
episode: 212 training return: tensor(-6685.5708, device='cuda:0')
episode: 213 training return: tensor(-7605.5811, device='cuda:0')
episode: 214 training return: tensor(-222430.0469, device='cuda:0')
episode: 215 training return: tensor(-6635.8960, device='cuda:0')
epoch: 54 test_true_pfm: 85.98113974354116
episode: 216 training return: tensor(-202567.3594, device='cuda:0')
episode: 217 training return: tensor(-7107.3364, device='cuda:0')
episode: 218 training return: tensor(-6155.5166, device='cuda:0')
episode: 219 training return: tensor(-12925.9004, device='cuda:0')
epoch: 55 test_true_pfm: -4.305015316009309
episode: 220 training return: tensor(-72555.3984, device='cuda:0')
episode: 221 training return: tensor(-6670.9756, device='cuda:0')
episode: 222 training return: tensor(-65329.5625, device='cuda:0')
episode: 223 training return: tensor(-162577.7656, device='cuda:0')
epoch: 56 test_true_pfm: -57.87462816931719
episode: 224 training return: tensor(-182020., device='cuda:0')
episode: 225 training return: tensor(-186542.8750, device='cuda:0')
episode: 226 training return: tensor(-320381.3125, device='cuda:0')
episode: 227 training return: tensor(-6567.2627, device='cuda:0')
epoch: 57 test_true_pfm: -57.411024428964026
episode: 228 training return: tensor(-26522.7637, device='cuda:0')
episode: 229 training return: tensor(-8582.2549, device='cuda:0')
episode: 230 training return: tensor(-6385.3716, device='cuda:0')
episode: 231 training return: tensor(-5938.0239, device='cuda:0')
epoch: 58 test_true_pfm: -6.375180849781333
episode: 232 training return: tensor(-8649.5654, device='cuda:0')
episode: 233 training return: tensor(-7172.8506, device='cuda:0')
episode: 234 training return: tensor(-7574.6904, device='cuda:0')
episode: 235 training return: tensor(-9204.5654, device='cuda:0')
epoch: 59 test_true_pfm: 0.8947604621606023
episode: 236 training return: tensor(-8644.4385, device='cuda:0')
episode: 237 training return: tensor(-7497.2217, device='cuda:0')
episode: 238 training return: tensor(-6631.3599, device='cuda:0')
episode: 239 training return: tensor(-132661.4531, device='cuda:0')
epoch: 60 test_true_pfm: -0.6304300836250102
episode: 240 training return: tensor(-50684504., device='cuda:0')
episode: 241 training return: tensor(-108663.2109, device='cuda:0')
episode: 242 training return: tensor(-6578.0259, device='cuda:0')
episode: 243 training return: tensor(-45118.3008, device='cuda:0')
epoch: 61 test_true_pfm: 61.00909319244022
episode: 244 training return: tensor(-36418.1680, device='cuda:0')
episode: 245 training return: tensor(-38704.1719, device='cuda:0')
episode: 246 training return: tensor(-58174.5117, device='cuda:0')
episode: 247 training return: tensor(-29697.3770, device='cuda:0')
epoch: 62 test_true_pfm: 104.85855856649677
episode: 248 training return: tensor(-55366.4180, device='cuda:0')
episode: 249 training return: tensor(-49364.8984, device='cuda:0')
episode: 250 training return: tensor(-54344.7383, device='cuda:0')
episode: 251 training return: tensor(-10566.9297, device='cuda:0')
epoch: 63 test_true_pfm: -13.381877432949503
episode: 252 training return: tensor(-9986.7539, device='cuda:0')
episode: 253 training return: tensor(-38940.6172, device='cuda:0')
episode: 254 training return: tensor(-12896.7510, device='cuda:0')
episode: 255 training return: tensor(-40547.7383, device='cuda:0')
epoch: 64 test_true_pfm: 75.82042573943859
episode: 256 training return: tensor(-103520.2891, device='cuda:0')
episode: 257 training return: tensor(-206748.1562, device='cuda:0')
episode: 258 training return: tensor(-206070.4688, device='cuda:0')
episode: 259 training return: tensor(-175147.0156, device='cuda:0')
epoch: 65 test_true_pfm: -5.468092585016286
episode: 260 training return: tensor(-143455.8750, device='cuda:0')
episode: 261 training return: tensor(-199509.7188, device='cuda:0')
episode: 262 training return: tensor(-243790.1875, device='cuda:0')
episode: 263 training return: tensor(-264176.3438, device='cuda:0')
epoch: 66 test_true_pfm: -151.67064327253186
episode: 264 training return: tensor(-11862.5742, device='cuda:0')
episode: 265 training return: tensor(-226067.3594, device='cuda:0')
episode: 266 training return: tensor(-247112.5312, device='cuda:0')
episode: 267 training return: tensor(-360846.9062, device='cuda:0')
epoch: 67 test_true_pfm: -32.98754060148725
episode: 268 training return: tensor(-248774.1406, device='cuda:0')
episode: 269 training return: tensor(-432736., device='cuda:0')
episode: 270 training return: tensor(-14111.0742, device='cuda:0')
episode: 271 training return: tensor(-206676.1562, device='cuda:0')
epoch: 68 test_true_pfm: -29.47890570987057
episode: 272 training return: tensor(-217817.6250, device='cuda:0')
episode: 273 training return: tensor(-214439.5469, device='cuda:0')
episode: 274 training return: tensor(-10225.4590, device='cuda:0')
episode: 275 training return: tensor(-244639.9844, device='cuda:0')
epoch: 69 test_true_pfm: 137.72271883203362
episode: 276 training return: tensor(-83284.3125, device='cuda:0')
episode: 277 training return: tensor(-71332.9219, device='cuda:0')
episode: 278 training return: tensor(-2.9773e+08, device='cuda:0')
episode: 279 training return: tensor(-236812.2500, device='cuda:0')
epoch: 70 test_true_pfm: -98.8569878959418
episode: 280 training return: tensor(-263322.1250, device='cuda:0')
episode: 281 training return: tensor(-451484.5938, device='cuda:0')
episode: 282 training return: tensor(-10638.3477, device='cuda:0')
episode: 283 training return: tensor(-79272936., device='cuda:0')
epoch: 71 test_true_pfm: 68.95552239649747
episode: 284 training return: tensor(-178199.9375, device='cuda:0')
episode: 285 training return: tensor(-280435.6562, device='cuda:0')
episode: 286 training return: tensor(-112946.1641, device='cuda:0')
episode: 287 training return: tensor(-7396.3730, device='cuda:0')
epoch: 72 test_true_pfm: -22.708634692258695
episode: 288 training return: tensor(-194045.7969, device='cuda:0')
episode: 289 training return: tensor(-61376.4961, device='cuda:0')
episode: 290 training return: tensor(-7293.0635, device='cuda:0')
episode: 291 training return: tensor(-7309.8896, device='cuda:0')
epoch: 73 test_true_pfm: -98.80819261805921
episode: 292 training return: tensor(-46946.5039, device='cuda:0')
episode: 293 training return: tensor(-47099.2461, device='cuda:0')
episode: 294 training return: tensor(-21949.0273, device='cuda:0')
episode: 295 training return: tensor(-74889.8281, device='cuda:0')
epoch: 74 test_true_pfm: -42.99370687435313
episode: 296 training return: tensor(-8010.8765, device='cuda:0')
episode: 297 training return: tensor(-46457.3359, device='cuda:0')
episode: 298 training return: tensor(-77210.3047, device='cuda:0')
episode: 299 training return: tensor(-6968.1084, device='cuda:0')
epoch: 75 test_true_pfm: -118.21077477829097
episode: 300 training return: tensor(-9148.2705, device='cuda:0')
episode: 301 training return: tensor(-9560.0420, device='cuda:0')
episode: 302 training return: tensor(-53931.3789, device='cuda:0')
episode: 303 training return: tensor(-9778.0918, device='cuda:0')
epoch: 76 test_true_pfm: 9.324343465970529
episode: 304 training return: tensor(-8404.9502, device='cuda:0')
episode: 305 training return: tensor(-143858.3125, device='cuda:0')
episode: 306 training return: tensor(-9264.8779, device='cuda:0')
episode: 307 training return: tensor(-249558.0938, device='cuda:0')
epoch: 77 test_true_pfm: -43.94325869906328
episode: 308 training return: tensor(-196068.7656, device='cuda:0')
episode: 309 training return: tensor(-210009.2969, device='cuda:0')
episode: 310 training return: tensor(-53710.5117, device='cuda:0')
episode: 311 training return: tensor(-9480.2939, device='cuda:0')
epoch: 78 test_true_pfm: -40.73697253157736
episode: 312 training return: tensor(-241924.4531, device='cuda:0')
episode: 313 training return: tensor(-22448.6426, device='cuda:0')
episode: 314 training return: tensor(-250036.6562, device='cuda:0')
episode: 315 training return: tensor(-241789.7344, device='cuda:0')
epoch: 79 test_true_pfm: 36.61250960199835
episode: 316 training return: tensor(-7334.1025, device='cuda:0')
episode: 317 training return: tensor(-38376.5039, device='cuda:0')
episode: 318 training return: tensor(-6933.5649, device='cuda:0')
episode: 319 training return: tensor(-202182.1250, device='cuda:0')
epoch: 80 test_true_pfm: -88.14521256217843
episode: 320 training return: tensor(-7519.2100, device='cuda:0')
episode: 321 training return: tensor(-12039.0010, device='cuda:0')
episode: 322 training return: tensor(-59015.6328, device='cuda:0')
episode: 323 training return: tensor(-226451.1562, device='cuda:0')
epoch: 81 test_true_pfm: -53.68814307532148
episode: 324 training return: tensor(-236782.1562, device='cuda:0')
episode: 325 training return: tensor(-51794.7891, device='cuda:0')
episode: 326 training return: tensor(-232859.2031, device='cuda:0')
episode: 327 training return: tensor(-10934.8818, device='cuda:0')
epoch: 82 test_true_pfm: 5.760655539630761
episode: 328 training return: tensor(-10866.7539, device='cuda:0')
episode: 329 training return: tensor(-8657.5752, device='cuda:0')
episode: 330 training return: tensor(-250195.0938, device='cuda:0')
episode: 331 training return: tensor(-243018.8125, device='cuda:0')
epoch: 83 test_true_pfm: -75.26858619203124
episode: 332 training return: tensor(-215635.0625, device='cuda:0')
episode: 333 training return: tensor(-72796.7422, device='cuda:0')
episode: 334 training return: tensor(-9142.0273, device='cuda:0')
episode: 335 training return: tensor(-238852.4219, device='cuda:0')
epoch: 84 test_true_pfm: -32.165421710960366
episode: 336 training return: tensor(-9184.8008, device='cuda:0')
episode: 337 training return: tensor(-226792.3594, device='cuda:0')
episode: 338 training return: tensor(-138056.5469, device='cuda:0')
episode: 339 training return: tensor(-7782.4126, device='cuda:0')
epoch: 85 test_true_pfm: -27.92219769187291
episode: 340 training return: tensor(-9587.9580, device='cuda:0')
episode: 341 training return: tensor(-8591.0410, device='cuda:0')
episode: 342 training return: tensor(-229238.8281, device='cuda:0')
episode: 343 training return: tensor(-8522.6963, device='cuda:0')
epoch: 86 test_true_pfm: -36.208487951096515
episode: 344 training return: tensor(-9036.7891, device='cuda:0')
episode: 345 training return: tensor(-6642.2178, device='cuda:0')
episode: 346 training return: tensor(-219371.2500, device='cuda:0')
episode: 347 training return: tensor(-106090.2656, device='cuda:0')
epoch: 87 test_true_pfm: -29.07467710002089
episode: 348 training return: tensor(-57625.3906, device='cuda:0')
episode: 349 training return: tensor(-122055.0625, device='cuda:0')
episode: 350 training return: tensor(-95866.3594, device='cuda:0')
episode: 351 training return: tensor(-6919.8154, device='cuda:0')
epoch: 88 test_true_pfm: -13.43352131027651
episode: 352 training return: tensor(-24924.1445, device='cuda:0')
episode: 353 training return: tensor(-171289.4062, device='cuda:0')
episode: 354 training return: tensor(-256983.2969, device='cuda:0')
episode: 355 training return: tensor(-209824.7656, device='cuda:0')
epoch: 89 test_true_pfm: 70.9093046717998
episode: 356 training return: tensor(-189892.6094, device='cuda:0')
episode: 357 training return: tensor(-253951.3750, device='cuda:0')
episode: 358 training return: tensor(-357937.3750, device='cuda:0')
episode: 359 training return: tensor(-218560.2812, device='cuda:0')
epoch: 90 test_true_pfm: -41.84526629824658
episode: 360 training return: tensor(-9066.5879, device='cuda:0')
episode: 361 training return: tensor(-7339.0645, device='cuda:0')
episode: 362 training return: tensor(-8887.7158, device='cuda:0')
episode: 363 training return: tensor(-207274.6875, device='cuda:0')
epoch: 91 test_true_pfm: -56.79699686260498
episode: 364 training return: tensor(-42927.6797, device='cuda:0')
episode: 365 training return: tensor(-7217.0391, device='cuda:0')
episode: 366 training return: tensor(-7993.0684, device='cuda:0')
episode: 367 training return: tensor(-102206.7812, device='cuda:0')
epoch: 92 test_true_pfm: -92.40153754781203
episode: 368 training return: tensor(-8305.0303, device='cuda:0')
episode: 369 training return: tensor(-8899.1494, device='cuda:0')
episode: 370 training return: tensor(-9689.9727, device='cuda:0')
episode: 371 training return: tensor(-8536.4727, device='cuda:0')
epoch: 93 test_true_pfm: 60.442607955098914
episode: 372 training return: tensor(-7971.6084, device='cuda:0')
episode: 373 training return: tensor(-7406.2378, device='cuda:0')
episode: 374 training return: tensor(-39507.5352, device='cuda:0')
episode: 375 training return: tensor(-41391.1836, device='cuda:0')
epoch: 94 test_true_pfm: -6.055535385105874
episode: 376 training return: tensor(-37801.3516, device='cuda:0')
episode: 377 training return: tensor(-7300.9678, device='cuda:0')
episode: 378 training return: tensor(-6626.5469, device='cuda:0')
episode: 379 training return: tensor(-8739.9678, device='cuda:0')
epoch: 95 test_true_pfm: -68.74351629376788
episode: 380 training return: tensor(-7088.1899, device='cuda:0')
episode: 381 training return: tensor(-7805.3789, device='cuda:0')
episode: 382 training return: tensor(-18544.9590, device='cuda:0')
episode: 383 training return: tensor(-6526.3799, device='cuda:0')
epoch: 96 test_true_pfm: -12.119275919520637
episode: 384 training return: tensor(-10611.4727, device='cuda:0')
episode: 385 training return: tensor(-66320.2812, device='cuda:0')
episode: 386 training return: tensor(-9227.0908, device='cuda:0')
episode: 387 training return: tensor(-96074.1094, device='cuda:0')
epoch: 97 test_true_pfm: -46.97476429949541
episode: 388 training return: tensor(-106985.0312, device='cuda:0')
episode: 389 training return: tensor(-9313.2588, device='cuda:0')
episode: 390 training return: tensor(-7675.1143, device='cuda:0')
episode: 391 training return: tensor(-31489.1621, device='cuda:0')
epoch: 98 test_true_pfm: -29.633379340901865
episode: 392 training return: tensor(-7077.1807, device='cuda:0')
episode: 393 training return: tensor(-10280.6416, device='cuda:0')
episode: 394 training return: tensor(-6670.5654, device='cuda:0')
episode: 395 training return: tensor(-6483.5215, device='cuda:0')
epoch: 99 test_true_pfm: -65.09108396551851
episode: 396 training return: tensor(-6841.7959, device='cuda:0')
episode: 397 training return: tensor(-8210.8701, device='cuda:0')
episode: 398 training return: tensor(-31554.8340, device='cuda:0')
episode: 399 training return: tensor(-40981.3477, device='cuda:0')
epoch: 100 test_true_pfm: 27.02924989173424
episode: 400 training return: tensor(-10775., device='cuda:0')
episode: 401 training return: tensor(-9138.0049, device='cuda:0')
episode: 402 training return: tensor(-38686.5859, device='cuda:0')
episode: 403 training return: tensor(-5990.8472, device='cuda:0')
epoch: 101 test_true_pfm: -30.827304091414437
episode: 404 training return: tensor(-7145.8813, device='cuda:0')
episode: 405 training return: tensor(-9460.5127, device='cuda:0')
episode: 406 training return: tensor(-7085.3545, device='cuda:0')
episode: 407 training return: tensor(-7534.3804, device='cuda:0')
epoch: 102 test_true_pfm: -26.408087867015922
episode: 408 training return: tensor(-6660.5220, device='cuda:0')
episode: 409 training return: tensor(-6498.6548, device='cuda:0')
episode: 410 training return: tensor(-25828.4688, device='cuda:0')
episode: 411 training return: tensor(-32672.1582, device='cuda:0')
epoch: 103 test_true_pfm: -81.39765754419464
episode: 412 training return: tensor(-7144.8198, device='cuda:0')
episode: 413 training return: tensor(-8895.1777, device='cuda:0')
episode: 414 training return: tensor(-32943.6484, device='cuda:0')
episode: 415 training return: tensor(-7098.8496, device='cuda:0')
epoch: 104 test_true_pfm: -1.7507686579667308
episode: 416 training return: tensor(-56117.4023, device='cuda:0')
episode: 417 training return: tensor(-8935.5186, device='cuda:0')
episode: 418 training return: tensor(-8719.9336, device='cuda:0')
episode: 419 training return: tensor(-11983.2568, device='cuda:0')
epoch: 105 test_true_pfm: -3.8256221148011655
episode: 420 training return: tensor(-8439.4023, device='cuda:0')
episode: 421 training return: tensor(-11168.0371, device='cuda:0')
episode: 422 training return: tensor(-9310.0234, device='cuda:0')
episode: 423 training return: tensor(-22696.8438, device='cuda:0')
epoch: 106 test_true_pfm: -21.81624537629636
episode: 424 training return: tensor(-8212.2598, device='cuda:0')
episode: 425 training return: tensor(-8036.0664, device='cuda:0')
episode: 426 training return: tensor(-10607.3672, device='cuda:0')
episode: 427 training return: tensor(-6800.3862, device='cuda:0')
epoch: 107 test_true_pfm: 15.778916714477797
episode: 428 training return: tensor(-8708.2959, device='cuda:0')
episode: 429 training return: tensor(-9108.3994, device='cuda:0')
episode: 430 training return: tensor(-15601.0352, device='cuda:0')
episode: 431 training return: tensor(-11127.1631, device='cuda:0')
epoch: 108 test_true_pfm: 35.390176995662905
episode: 432 training return: tensor(-7907.5718, device='cuda:0')
episode: 433 training return: tensor(-9226.8789, device='cuda:0')
episode: 434 training return: tensor(-8778.0449, device='cuda:0')
episode: 435 training return: tensor(-95510.9531, device='cuda:0')
epoch: 109 test_true_pfm: -113.44209355833733
episode: 436 training return: tensor(-6797.7993, device='cuda:0')
episode: 437 training return: tensor(-6387.5010, device='cuda:0')
episode: 438 training return: tensor(-102287.8125, device='cuda:0')
episode: 439 training return: tensor(-41594.1641, device='cuda:0')
epoch: 110 test_true_pfm: -74.87685289903537
episode: 440 training return: tensor(-10731.0195, device='cuda:0')
episode: 441 training return: tensor(-18508.2559, device='cuda:0')
episode: 442 training return: tensor(-12102.9209, device='cuda:0')
episode: 443 training return: tensor(-40616.1094, device='cuda:0')
epoch: 111 test_true_pfm: 9.81817869695479
episode: 444 training return: tensor(-6952.2690, device='cuda:0')
episode: 445 training return: tensor(-6498.6958, device='cuda:0')
episode: 446 training return: tensor(-10489.2725, device='cuda:0')
episode: 447 training return: tensor(-9193.9404, device='cuda:0')
epoch: 112 test_true_pfm: 18.399557030094392
episode: 448 training return: tensor(-8416.9229, device='cuda:0')
episode: 449 training return: tensor(-9988.3311, device='cuda:0')
episode: 450 training return: tensor(-10643.5371, device='cuda:0')
episode: 451 training return: tensor(-10110.9209, device='cuda:0')
epoch: 113 test_true_pfm: -14.132582324159054
episode: 452 training return: tensor(-48468.8008, device='cuda:0')
episode: 453 training return: tensor(-10657.4775, device='cuda:0')
episode: 454 training return: tensor(-261577.9531, device='cuda:0')
episode: 455 training return: tensor(-112975.9609, device='cuda:0')
epoch: 114 test_true_pfm: -22.966642745890038
episode: 456 training return: tensor(-6926.6172, device='cuda:0')
episode: 457 training return: tensor(-27694.6211, device='cuda:0')
episode: 458 training return: tensor(-13839.4531, device='cuda:0')
episode: 459 training return: tensor(-137418.5156, device='cuda:0')
epoch: 115 test_true_pfm: -43.999838972048316
episode: 460 training return: tensor(-7819.1357, device='cuda:0')
episode: 461 training return: tensor(-104054.9297, device='cuda:0')
episode: 462 training return: tensor(-249236.1875, device='cuda:0')
episode: 463 training return: tensor(-110692.9688, device='cuda:0')
epoch: 116 test_true_pfm: -132.8859931515507
episode: 464 training return: tensor(-46287.4219, device='cuda:0')
episode: 465 training return: tensor(-32795.3516, device='cuda:0')
episode: 466 training return: tensor(-23414.6543, device='cuda:0')
episode: 467 training return: tensor(-21650.3281, device='cuda:0')
epoch: 117 test_true_pfm: 4.570628750386994
episode: 468 training return: tensor(-8158.0063, device='cuda:0')
episode: 469 training return: tensor(-6923.4487, device='cuda:0')
episode: 470 training return: tensor(-51390.7891, device='cuda:0')
episode: 471 training return: tensor(-39783.2930, device='cuda:0')
epoch: 118 test_true_pfm: -91.4012510532108
episode: 472 training return: tensor(-6366.8306, device='cuda:0')
episode: 473 training return: tensor(-9189.8438, device='cuda:0')
episode: 474 training return: tensor(-33290.7266, device='cuda:0')
episode: 475 training return: tensor(-16562.0645, device='cuda:0')
epoch: 119 test_true_pfm: -21.713791573631113
episode: 476 training return: tensor(-8315.3418, device='cuda:0')
episode: 477 training return: tensor(-41104.8438, device='cuda:0')
episode: 478 training return: tensor(-13743.4746, device='cuda:0')
episode: 479 training return: tensor(-14546.3740, device='cuda:0')
epoch: 120 test_true_pfm: -112.15870089112936
episode: 480 training return: tensor(-41513.7148, device='cuda:0')
episode: 481 training return: tensor(-12363.1621, device='cuda:0')
episode: 482 training return: tensor(-29617.6914, device='cuda:0')
episode: 483 training return: tensor(-40151.7344, device='cuda:0')
epoch: 121 test_true_pfm: -106.32088618610625
episode: 484 training return: tensor(-68932.8438, device='cuda:0')
episode: 485 training return: tensor(-141780.7812, device='cuda:0')
episode: 486 training return: tensor(-98754.3359, device='cuda:0')
episode: 487 training return: tensor(-89145.2656, device='cuda:0')
epoch: 122 test_true_pfm: -111.97388026298258
episode: 488 training return: tensor(-245853.2344, device='cuda:0')
episode: 489 training return: tensor(-60009.5703, device='cuda:0')
episode: 490 training return: tensor(-11072.0879, device='cuda:0')
episode: 491 training return: tensor(-258934.9062, device='cuda:0')
epoch: 123 test_true_pfm: -3.827243571244388
episode: 492 training return: tensor(-67087.0156, device='cuda:0')
episode: 493 training return: tensor(-30657.6172, device='cuda:0')
episode: 494 training return: tensor(-10088.2725, device='cuda:0')
episode: 495 training return: tensor(-12041.7090, device='cuda:0')
epoch: 124 test_true_pfm: 20.779248585803348
episode: 496 training return: tensor(-81119.6094, device='cuda:0')
episode: 497 training return: tensor(-41632.5586, device='cuda:0')
episode: 498 training return: tensor(-105569.2734, device='cuda:0')
episode: 499 training return: tensor(-18773.1309, device='cuda:0')
epoch: 125 test_true_pfm: -94.61273043509858
episode: 500 training return: tensor(-73003.5625, device='cuda:0')
episode: 501 training return: tensor(-289385.1250, device='cuda:0')
episode: 502 training return: tensor(-11174.2744, device='cuda:0')
episode: 503 training return: tensor(-9131.2881, device='cuda:0')
epoch: 126 test_true_pfm: -192.21766885905674
episode: 504 training return: tensor(-148793.6562, device='cuda:0')
episode: 505 training return: tensor(-36378.3867, device='cuda:0')
episode: 506 training return: tensor(-59124.7422, device='cuda:0')
episode: 507 training return: tensor(-11179.5469, device='cuda:0')
epoch: 127 test_true_pfm: -283.0219150150661
episode: 508 training return: tensor(-160572.1406, device='cuda:0')
episode: 509 training return: tensor(-114159.9375, device='cuda:0')
episode: 510 training return: tensor(-69551.2656, device='cuda:0')
episode: 511 training return: tensor(-46235.2109, device='cuda:0')
epoch: 128 test_true_pfm: -75.69795215779173
episode: 512 training return: tensor(-11062.0566, device='cuda:0')
episode: 513 training return: tensor(-37572.7422, device='cuda:0')
episode: 514 training return: tensor(-14798.0684, device='cuda:0')
episode: 515 training return: tensor(-211093.2656, device='cuda:0')
epoch: 129 test_true_pfm: -51.85278957668198
episode: 516 training return: tensor(-44342.0703, device='cuda:0')
episode: 517 training return: tensor(-44223.5234, device='cuda:0')
episode: 518 training return: tensor(-11260.6377, device='cuda:0')
episode: 519 training return: tensor(-29275.0840, device='cuda:0')
epoch: 130 test_true_pfm: -79.40516568475313
episode: 520 training return: tensor(-80386.4141, device='cuda:0')
episode: 521 training return: tensor(-13118.9658, device='cuda:0')
episode: 522 training return: tensor(-59660.6523, device='cuda:0')
episode: 523 training return: tensor(-34941.9805, device='cuda:0')
epoch: 131 test_true_pfm: -31.327628370135837
episode: 524 training return: tensor(-17219.1094, device='cuda:0')
episode: 525 training return: tensor(-81144.3984, device='cuda:0')
episode: 526 training return: tensor(-47058.1797, device='cuda:0')
episode: 527 training return: tensor(-64737.8750, device='cuda:0')
epoch: 132 test_true_pfm: -63.79763007793999
episode: 528 training return: tensor(-8275.0303, device='cuda:0')
episode: 529 training return: tensor(-10417.6748, device='cuda:0')
episode: 530 training return: tensor(-40063.8047, device='cuda:0')
episode: 531 training return: tensor(-12911.9443, device='cuda:0')
epoch: 133 test_true_pfm: -117.67699832911842
episode: 532 training return: tensor(-20839.6836, device='cuda:0')
episode: 533 training return: tensor(-17620.0566, device='cuda:0')
episode: 534 training return: tensor(-9556.7168, device='cuda:0')
episode: 535 training return: tensor(-39428.3242, device='cuda:0')
epoch: 134 test_true_pfm: -108.08080613933244
episode: 536 training return: tensor(-14395.9043, device='cuda:0')
episode: 537 training return: tensor(-65261.8711, device='cuda:0')
episode: 538 training return: tensor(-68496.4766, device='cuda:0')
episode: 539 training return: tensor(-9096.9980, device='cuda:0')
epoch: 135 test_true_pfm: 82.61893215036129
episode: 540 training return: tensor(-8214.2705, device='cuda:0')
episode: 541 training return: tensor(-60384.2109, device='cuda:0')
episode: 542 training return: tensor(-8155.6016, device='cuda:0')
episode: 543 training return: tensor(-72016.4141, device='cuda:0')
epoch: 136 test_true_pfm: -138.15914280298375
episode: 544 training return: tensor(-61338.0664, device='cuda:0')
episode: 545 training return: tensor(-68614.1172, device='cuda:0')
episode: 546 training return: tensor(-57227.6758, device='cuda:0')
episode: 547 training return: tensor(-95776.8203, device='cuda:0')
epoch: 137 test_true_pfm: -124.84708690471
episode: 548 training return: tensor(-104896.6719, device='cuda:0')
episode: 549 training return: tensor(-126325.2969, device='cuda:0')
episode: 550 training return: tensor(-98567.9062, device='cuda:0')
episode: 551 training return: tensor(-79553.1016, device='cuda:0')
epoch: 138 test_true_pfm: -148.43401167954457
episode: 552 training return: tensor(-29667.9336, device='cuda:0')
episode: 553 training return: tensor(-56477.9297, device='cuda:0')
episode: 554 training return: tensor(-64444.8477, device='cuda:0')
episode: 555 training return: tensor(-71420.8984, device='cuda:0')
epoch: 139 test_true_pfm: -490.0557978615129
episode: 556 training return: tensor(-75004.5156, device='cuda:0')
episode: 557 training return: tensor(-47651.8750, device='cuda:0')
episode: 558 training return: tensor(-32202.4668, device='cuda:0')
episode: 559 training return: tensor(-18783.6367, device='cuda:0')
epoch: 140 test_true_pfm: -99.46653106934646
episode: 560 training return: tensor(-46277.4297, device='cuda:0')
episode: 561 training return: tensor(-42812.9414, device='cuda:0')
episode: 562 training return: tensor(-43732.6289, device='cuda:0')
episode: 563 training return: tensor(-69823.2578, device='cuda:0')
epoch: 141 test_true_pfm: 105.23400119929467
episode: 564 training return: tensor(-65310.6953, device='cuda:0')
episode: 565 training return: tensor(-99598.9609, device='cuda:0')
episode: 566 training return: tensor(-80204.9922, device='cuda:0')
episode: 567 training return: tensor(-52852.4492, device='cuda:0')
epoch: 142 test_true_pfm: -164.33082216942367
episode: 568 training return: tensor(-17576.7031, device='cuda:0')
episode: 569 training return: tensor(-63591.4844, device='cuda:0')
episode: 570 training return: tensor(-52175.3945, device='cuda:0')
episode: 571 training return: tensor(-108829.4688, device='cuda:0')
epoch: 143 test_true_pfm: -307.93902256648687
episode: 572 training return: tensor(-51434.0312, device='cuda:0')
episode: 573 training return: tensor(-39650.4570, device='cuda:0')
episode: 574 training return: tensor(-180734.9844, device='cuda:0')
episode: 575 training return: tensor(-32661.9199, device='cuda:0')
epoch: 144 test_true_pfm: -111.11280530219187
episode: 576 training return: tensor(-71460.5000, device='cuda:0')
episode: 577 training return: tensor(-11725.8389, device='cuda:0')
episode: 578 training return: tensor(-98097.9766, device='cuda:0')
episode: 579 training return: tensor(-31593.5176, device='cuda:0')
epoch: 145 test_true_pfm: -109.97043631396099
episode: 580 training return: tensor(-25218.0410, device='cuda:0')
episode: 581 training return: tensor(-32315.6582, device='cuda:0')
episode: 582 training return: tensor(-6670.4897, device='cuda:0')
episode: 583 training return: tensor(-64206.0742, device='cuda:0')
epoch: 146 test_true_pfm: -297.56364881871286
episode: 584 training return: tensor(-9747.2617, device='cuda:0')
episode: 585 training return: tensor(-9407.4678, device='cuda:0')
episode: 586 training return: tensor(-15448.2148, device='cuda:0')
episode: 587 training return: tensor(-9410.9443, device='cuda:0')
epoch: 147 test_true_pfm: -87.00695462960714
episode: 588 training return: tensor(-5662.1450, device='cuda:0')
episode: 589 training return: tensor(-7883.6797, device='cuda:0')
episode: 590 training return: tensor(-10651.3252, device='cuda:0')
episode: 591 training return: tensor(-49720.8672, device='cuda:0')
epoch: 148 test_true_pfm: -85.03531720015101
episode: 592 training return: tensor(-33946.3477, device='cuda:0')
episode: 593 training return: tensor(-10337.6338, device='cuda:0')
episode: 594 training return: tensor(-9490.3223, device='cuda:0')
episode: 595 training return: tensor(-8022.3921, device='cuda:0')
epoch: 149 test_true_pfm: -145.9486267762203
episode: 596 training return: tensor(-11356.8779, device='cuda:0')
episode: 597 training return: tensor(-9334.4141, device='cuda:0')
episode: 598 training return: tensor(-9545.3311, device='cuda:0')
episode: 599 training return: tensor(-9429.4502, device='cuda:0')
epoch: 150 test_true_pfm: 127.10443432644392
