Expert(Sto) Return Avg: 12348.65, std: 1216.54
array([12641.39 , 12459.417, 12260.102, 12733.071, 12399.556, 12505.918,
       12571.552, 12182.177, 12565.865, 12579.269, 12882.325, 12691.728,
       12642.594, 12557.986,  4063.388,  7720.289, 12707.304, 12578.79 ,
       12513.988, 12725.935, 12644.522, 12960.425, 12379.737, 12377.187,
       12294.647, 12512.517, 12766.553, 12442.338, 12439.016, 12630.503,
       12538.109, 12306.523, 12434.274, 12473.371, 12683.452, 12378.433,
       12492.347, 12592.625, 12455.264, 12514.309, 12658.811, 12239.684,
       12692.854, 12640.846, 12575.215, 12769.487, 12662.542, 12642.662,
       12266.904, 12530.063, 12428.621, 12519.222, 12789.527, 12610.419,
       12544.279, 12279.695, 13063.751, 12598.614, 12581.024, 12698.638,
       12238.495, 12460.419, 12640.41 , 12882.675])
Expert(Det) Return Avg: 12993.18, std: 140.72
array([13051.468, 13104.521, 12624.654, 13023.988, 13199.636, 13210.321,
       12944.966, 12919.647, 12915.541, 13030.77 , 13012.786, 13090.878,
       12767.247, 13087.571, 13064.647, 13248.452, 12995.339, 13021.479,
       12814.199, 12939.253, 12753.607, 12771.955, 12859.397, 12624.707,
       12931.257, 13100.75 , 13075.588, 13065.268, 13191.632, 12950.689,
       12792.689, 12931.85 , 12994.969, 12844.103, 12799.64 , 12945.846,
       13058.229, 13071.526, 12932.891, 12744.601, 13173.479, 13023.371,
       13124.521, 13029.426, 12994.994, 13114.163, 13079.317, 13165.854,
       12844.015, 12959.781, 13170.385, 12989.363, 13117.899, 12991.543,
       13101.453, 13118.265, 12733.602, 13118.114, 12906.983, 12977.713,
       13091.129, 13097.802, 13054.699, 13077.091])
ordereddict([('seed', 666), ('cuda', -1), ('env', ordereddict([('env_name', 'HalfCheetahFH-v0'), ('T', 1000)])), ('sac', ordereddict([('epochs', 3000), ('log_step_interval', 5000), ('update_every', 50), ('update_num', 1), ('random_explore_episodes', 10), ('batch_size', 100), ('lr', 0.001), ('alpha', 0.2), ('automatic_alpha_tuning', False), ('buffer_size', 1000000), ('num_test_episodes', 10)])), ('expert', ordereddict([('samples_episode', 64)])), ('launching_env', 'halfcheetah'), ('_hidden_keys', []), ('exp_cnt', 3), ('exp_name', '7-16-sac-samples_2020_07_16_20_24_30_0004')])