0000000000000000000000000000000000000000 0f46d46ec10170cc7b99f63757a383df6928bfe4 HFML <rw422@tamu.edu> 1676846315 -0600	clone: from https://github.com/marc-rigter/rambo.git
0f46d46ec10170cc7b99f63757a383df6928bfe4 0f46d46ec10170cc7b99f63757a383df6928bfe4 HFML <rw422@tamu.edu> 1676848830 -0600	checkout: moving from master to test
0f46d46ec10170cc7b99f63757a383df6928bfe4 3429fd6b54996704f09bdf7de5e8c5b437b36481 HFML <rw422@tamu.edu> 1680127424 -0500	commit: add model and stats logging, add additional training arguments
3429fd6b54996704f09bdf7de5e8c5b437b36481 1796d4b815065a76bef3d801ef7ad4d96106eb25 HFML <rw422@tamu.edu> 1680128044 -0500	commit: initial commit rail
1796d4b815065a76bef3d801ef7ad4d96106eb25 331ad68f19e90f6ec2f7cef93137f30a2aec170e HFML <rw422@tamu.edu> 1680141815 -0500	commit: commit rail algorithm
331ad68f19e90f6ec2f7cef93137f30a2aec170e 51711c7802dbaded902c4d4ba6507ce3433921bf HFML <rw422@tamu.edu> 1680142529 -0500	commit (amend): commit rail algorithm
51711c7802dbaded902c4d4ba6507ce3433921bf a0e9bcf2e6779f6da965449db5f65f0f6063eee5 HFML <rw422@tamu.edu> 1680190913 -0500	commit: add terminal flag to reward model, handle terminal value function
a0e9bcf2e6779f6da965449db5f65f0f6063eee5 46dc0f69abad23c82f0cb736e01f99c011a864bf HFML <rw422@tamu.edu> 1680206570 -0500	commit: add expert pool to rail algorithm and add expert pool option to all config files
46dc0f69abad23c82f0cb736e01f99c011a864bf c44d201df130e2ccba983854caa26c497de511dc HFML <rw422@tamu.edu> 1680367557 -0500	commit: add code for fixed sac temperature
c44d201df130e2ccba983854caa26c497de511dc fd616cc952b508cf86806b0f4bc1fcc5d0f2a473 HFML <rw422@tamu.edu> 1680382141 -0500	commit: add trajectory based reward update method
fd616cc952b508cf86806b0f4bc1fcc5d0f2a473 e33980a18b53e0a6840756c60f7b413e438cca19 HFML <rw422@tamu.edu> 1680552748 -0500	commit: add bug fix rail compute_reward done_flag and reward_loss normalization, add adv and obs loss tracking
e33980a18b53e0a6840756c60f7b413e438cca19 4ab2c6ef7ac9667c9b840591f1098329675a5bc1 HFML <rw422@tamu.edu> 1680890804 -0500	commit: tidy up rambo logging directories
4ab2c6ef7ac9667c9b840591f1098329675a5bc1 179d1e501232f2210141c0ac779485c3f3e438a1 HFML <rw422@tamu.edu> 1680902391 -0500	commit: add normalizations to loader functions
179d1e501232f2210141c0ac779485c3f3e438a1 d8d917a18afad1bb1c84aa5cb95d1619690b5795 HFML <rw422@tamu.edu> 1680902666 -0500	commit: modify expert trajectory normalization
d8d917a18afad1bb1c84aa5cb95d1619690b5795 c892fa6ca1389f69dd4b2a0dd59d544952a063e4 HFML <rw422@tamu.edu> 1681140575 -0500	commit: fix author adv_loss normalization bug and change adv_weighting, add config saving to rail and rambo, fix d4rl data loading bug
c892fa6ca1389f69dd4b2a0dd59d544952a063e4 a8a3f656854c7e6e56c5badcd7c817af703a0532 HFML <rw422@tamu.edu> 1681225716 -0500	commit (amend): fix author adv_loss normalization bug and change adv_weighting, add config saving to rail and rambo, fix d4rl data loading bug
a8a3f656854c7e6e56c5badcd7c817af703a0532 73812e708167a3c9451700650b4da6f2e409c34b HFML <rw422@tamu.edu> 1681764861 -0500	commit: rename rail to rirl
73812e708167a3c9451700650b4da6f2e409c34b 7e12435e0c4e554e70c44031eaa31615848173c2 HFML <rw422@tamu.edu> 1681765658 -0500	commit: rename rail configs to rirl
7e12435e0c4e554e70c44031eaa31615848173c2 600013e2ae919e6780cb3f0221fd44fd283469a0 HFML <rw422@tamu.edu> 1681765746 -0500	commit: correct d4rl data parsing
600013e2ae919e6780cb3f0221fd44fd283469a0 6f13ba31ff0f48906634aab114b935f51a741d2f HFML <rw422@tamu.edu> 1681765824 -0500	commit: rename rail to rirl in softlearning experiment step utils, handle nan actions in simple_sampler
6f13ba31ff0f48906634aab114b935f51a741d2f 53d706893bc70d1d180360c66481966a987495c2 HFML <rw422@tamu.edu> 1681766607 -0500	commit: remove random tasks
53d706893bc70d1d180360c66481966a987495c2 14b66c7dbf4046b7cddd467491ebdbfde59a6ae3 HFML <rw422@tamu.edu> 1681780314 -0500	commit: commit restore_pool_from_d4rl_trajectories
14b66c7dbf4046b7cddd467491ebdbfde59a6ae3 502db020dd4c52a1c6d5f2eb2bb93c5954073cf4 HFML <rw422@tamu.edu> 1681780462 -0500	commit: update rirl
502db020dd4c52a1c6d5f2eb2bb93c5954073cf4 7b5b0cb90f1c085eed5bdb294f83df34dcec10bf HFML <rw422@tamu.edu> 1681780678 -0500	commit: commit working birl, although not stable at the end
7b5b0cb90f1c085eed5bdb294f83df34dcec10bf 14eaa9f5be8823181f60b612fa3826e7cc93aa2f HFML <rw422@tamu.edu> 1681781263 -0500	commit: commit updated birl and rirl configs, halfcheetah config is different from rest
14eaa9f5be8823181f60b612fa3826e7cc93aa2f 0887c76076729e7542f60203d1034204ec1a9edc HFML <rw422@tamu.edu> 1681783099 -0500	commit (amend): commit updated birl and rirl configs, halfcheetah config is different from rest
0887c76076729e7542f60203d1034204ec1a9edc 63ee10843d751191cb1958f2413716f4f0f13373 HFML <rw422@tamu.edu> 1681824143 -0500	commit: update to compare policy to expert data
63ee10843d751191cb1958f2413716f4f0f13373 7b22082694356c2c2f3bd204fa9936f4a0cfccbc HFML <rw422@tamu.edu> 1681846886 -0500	commit: minor fix walker2d-medium-replay config
7b22082694356c2c2f3bd204fa9936f4a0cfccbc 7b22082694356c2c2f3bd204fa9936f4a0cfccbc git stash <rw422@tamu.edu> 1681956793 -0500	reset: moving to HEAD
7b22082694356c2c2f3bd204fa9936f4a0cfccbc d8d917a18afad1bb1c84aa5cb95d1619690b5795 HFML <rw422@tamu.edu> 1681956797 -0500	checkout: moving from test to debug
d8d917a18afad1bb1c84aa5cb95d1619690b5795 7b22082694356c2c2f3bd204fa9936f4a0cfccbc HFML <rw422@tamu.edu> 1681957232 -0500	checkout: moving from debug to test
7b22082694356c2c2f3bd204fa9936f4a0cfccbc 7b22082694356c2c2f3bd204fa9936f4a0cfccbc git stash <rw422@tamu.edu> 1681957393 -0500	reset: moving to HEAD
7b22082694356c2c2f3bd204fa9936f4a0cfccbc d8d917a18afad1bb1c84aa5cb95d1619690b5795 HFML <rw422@tamu.edu> 1681957398 -0500	checkout: moving from test to debug
d8d917a18afad1bb1c84aa5cb95d1619690b5795 7b22082694356c2c2f3bd204fa9936f4a0cfccbc HFML <rw422@tamu.edu> 1681957472 -0500	checkout: moving from debug to test
7b22082694356c2c2f3bd204fa9936f4a0cfccbc 7b22082694356c2c2f3bd204fa9936f4a0cfccbc git stash <rw422@tamu.edu> 1681998194 -0500	reset: moving to HEAD
7b22082694356c2c2f3bd204fa9936f4a0cfccbc d8d917a18afad1bb1c84aa5cb95d1619690b5795 HFML <rw422@tamu.edu> 1681998199 -0500	checkout: moving from test to debug
d8d917a18afad1bb1c84aa5cb95d1619690b5795 7b22082694356c2c2f3bd204fa9936f4a0cfccbc HFML <rw422@tamu.edu> 1681998210 -0500	checkout: moving from debug to test
7b22082694356c2c2f3bd204fa9936f4a0cfccbc 7b22082694356c2c2f3bd204fa9936f4a0cfccbc git stash <rw422@tamu.edu> 1681998927 -0500	reset: moving to HEAD
7b22082694356c2c2f3bd204fa9936f4a0cfccbc d8d917a18afad1bb1c84aa5cb95d1619690b5795 HFML <rw422@tamu.edu> 1681998933 -0500	checkout: moving from test to debug
d8d917a18afad1bb1c84aa5cb95d1619690b5795 d8d917a18afad1bb1c84aa5cb95d1619690b5795 git stash <rw422@tamu.edu> 1682039439 -0500	reset: moving to HEAD
d8d917a18afad1bb1c84aa5cb95d1619690b5795 7b22082694356c2c2f3bd204fa9936f4a0cfccbc HFML <rw422@tamu.edu> 1682039443 -0500	checkout: moving from debug to test
7b22082694356c2c2f3bd204fa9936f4a0cfccbc 6e0af41a79b2a8bfffbf75facb56a7ab23e8ddc2 HFML <rw422@tamu.edu> 1682040293 -0500	commit: resolve halfcheetah debugging conflict by accident
6e0af41a79b2a8bfffbf75facb56a7ab23e8ddc2 6e0af41a79b2a8bfffbf75facb56a7ab23e8ddc2 git stash <rw422@tamu.edu> 1682093140 -0500	reset: moving to HEAD
6e0af41a79b2a8bfffbf75facb56a7ab23e8ddc2 d8d917a18afad1bb1c84aa5cb95d1619690b5795 HFML <rw422@tamu.edu> 1682093151 -0500	checkout: moving from test to debug
d8d917a18afad1bb1c84aa5cb95d1619690b5795 d8d917a18afad1bb1c84aa5cb95d1619690b5795 HFML <rw422@tamu.edu> 1682093685 -0500	reset: moving to HEAD
d8d917a18afad1bb1c84aa5cb95d1619690b5795 406205bb6f7948b9dd5adc38a78aacfc02839b29 HFML <rw422@tamu.edu> 1682100652 -0500	commit: commit updated rail code, ready to copy over
406205bb6f7948b9dd5adc38a78aacfc02839b29 6e0af41a79b2a8bfffbf75facb56a7ab23e8ddc2 HFML <rw422@tamu.edu> 1682101002 -0500	checkout: moving from debug to test
6e0af41a79b2a8bfffbf75facb56a7ab23e8ddc2 406205bb6f7948b9dd5adc38a78aacfc02839b29 HFML <rw422@tamu.edu> 1682101124 -0500	checkout: moving from test to debug
406205bb6f7948b9dd5adc38a78aacfc02839b29 800089e4f1cc45befc886b4a593ef466ca874f42 HFML <rw422@tamu.edu> 1682102283 -0500	commit (amend): commit updated rail code, ready to copy over
800089e4f1cc45befc886b4a593ef466ca874f42 6e0af41a79b2a8bfffbf75facb56a7ab23e8ddc2 HFML <rw422@tamu.edu> 1682102338 -0500	checkout: moving from debug to test
6e0af41a79b2a8bfffbf75facb56a7ab23e8ddc2 ff78f98851b8528eb1280ac6a06b3f5b691c3bdc HFML <rw422@tamu.edu> 1682114981 -0500	commit: remove nan handle in simple sampler, commit base config for halfcheetah debugging
ff78f98851b8528eb1280ac6a06b3f5b691c3bdc ff78f98851b8528eb1280ac6a06b3f5b691c3bdc git stash <rw422@tamu.edu> 1682114983 -0500	reset: moving to HEAD
ff78f98851b8528eb1280ac6a06b3f5b691c3bdc a8a3f656854c7e6e56c5badcd7c817af703a0532 HFML <rw422@tamu.edu> 1682114987 -0500	checkout: moving from test to debug2
a8a3f656854c7e6e56c5badcd7c817af703a0532 ff78f98851b8528eb1280ac6a06b3f5b691c3bdc HFML <rw422@tamu.edu> 1682115041 -0500	checkout: moving from debug2 to test
ff78f98851b8528eb1280ac6a06b3f5b691c3bdc ff78f98851b8528eb1280ac6a06b3f5b691c3bdc git stash <rw422@tamu.edu> 1682126644 -0500	reset: moving to HEAD
ff78f98851b8528eb1280ac6a06b3f5b691c3bdc 800089e4f1cc45befc886b4a593ef466ca874f42 HFML <rw422@tamu.edu> 1682126648 -0500	checkout: moving from test to debug
800089e4f1cc45befc886b4a593ef466ca874f42 68c7c9566d875b6aab1de6c39e793c2770cc2231 HFML <rw422@tamu.edu> 1682133593 -0500	commit: fix rail adversarial loss reward broadcasting bug, update all relevant hyperparameters
68c7c9566d875b6aab1de6c39e793c2770cc2231 ff78f98851b8528eb1280ac6a06b3f5b691c3bdc HFML <rw422@tamu.edu> 1682133603 -0500	checkout: moving from debug to test
ff78f98851b8528eb1280ac6a06b3f5b691c3bdc 3c58887a3956c781957ea721e06219225d159afc HFML <rw422@tamu.edu> 1682173067 -0500	commit: bug fix rirl adversarial loss broadcasting
3c58887a3956c781957ea721e06219225d159afc 1c14ba0c6d96d0faac9b8886c2cfb04ef181db61 HFML <rw422@tamu.edu> 1682198024 -0500	commit: commit working rirl and working halfcheetah medium expert config
1c14ba0c6d96d0faac9b8886c2cfb04ef181db61 8c6feaeea67e948a5fcd43af9e8017e9484f17f1 HFML <rw422@tamu.edu> 1682198378 -0500	commit (amend): commit working rirl and working halfcheetah medium expert config
8c6feaeea67e948a5fcd43af9e8017e9484f17f1 733bb8922e0fb65957926f089cc9f88bd031b474 HFML <rw422@tamu.edu> 1682262257 -0500	commit (amend): commit working rirl and working halfcheetah configs
733bb8922e0fb65957926f089cc9f88bd031b474 775a7a9442dd7a38fcbd9807d3e0aa7dd2707896 HFML <rw422@tamu.edu> 1682263513 -0500	commit (amend): commit working rirl and working halfcheetah configs
775a7a9442dd7a38fcbd9807d3e0aa7dd2707896 3c597b59b677b55fcba579cf0265dfc82b9a716f HFML <rw422@tamu.edu> 1682264901 -0500	commit (amend): commit working rirl and working halfcheetah configs
3c597b59b677b55fcba579cf0265dfc82b9a716f 053fcc20abd987cfcc11039410a61536097d5202 HFML <rw422@tamu.edu> 1682265028 -0500	commit: fix birl adversarial loss bug, update config, haven't tested hyperparameters
053fcc20abd987cfcc11039410a61536097d5202 d788e8b25c3b00b041f8d138612029717ee6b015 HFML <rw422@tamu.edu> 1682265830 -0500	commit (amend): fix birl adversarial loss bug, update config, haven't tested hyperparameters
d788e8b25c3b00b041f8d138612029717ee6b015 b5de16a40fe0a9c637600fbdf639e29b3734d438 HFML <rw422@tamu.edu> 1682265896 -0500	commit (amend): fix birl adversarial loss bug, update config, haven't tested hyperparameters
b5de16a40fe0a9c637600fbdf639e29b3734d438 e98bcb2d717b4f7b4b5cb3a208a66d3862a44bde HFML <rw422@tamu.edu> 1682265916 -0500	commit (amend): fix birl adversarial loss bug, update config, haven't tested hyperparameters
e98bcb2d717b4f7b4b5cb3a208a66d3862a44bde 398c4357bdd4d42881c63055afa671efac9f1add HFML <rw422@tamu.edu> 1682692273 -0500	commit: bug fix adversarial loss sample next obs
398c4357bdd4d42881c63055afa671efac9f1add 489c672f1f14f11a622f3eac2133c7248bfa9fce HFML <rw422@tamu.edu> 1682780192 -0500	commit: update birl hyperparameters
489c672f1f14f11a622f3eac2133c7248bfa9fce 8d8ad5577015a0e98bd00ef57cbab213c52db368 HFML <rw422@tamu.edu> 1686062232 -0500	commit: change algo docstring names
8d8ad5577015a0e98bd00ef57cbab213c52db368 7079828428983b89eae62557ca3278c2e9ba5c92 HFML <rw422@tamu.edu> 1686062256 -0500	commit: update readme
