Commits · 9916ea790848726edb31873294bfd6e003f82c9c · Wang, Mia / MetaRL

Apr 27, 2022
- fix mega_pol · 9916ea79
  Sun Jin Kim authored 2 years ago
  
  9916ea79
- write ucb_learner.get_mega_policy() and its test · 563fec38
  Sun Jin Kim authored 2 years ago
  
  563fec38
- aa_learner.history is now only updated in aa_learner._test_augoaugment_policy · 9605f53b
  Sun Jin Kim authored 2 years ago
  
  9605f53b
- corrected megapolicy · 1de0f23d
  Max Ramsay King authored 2 years ago
  
  1de0f23d
- full_pol to sub_pol · 926ee191
  Max Ramsay King authored 2 years ago
  
  926ee191
- pol_dict bug · 75083fc3
  Max Ramsay King authored 2 years ago
  
  75083fc3
- edit aa_learner.policy_record · 825b1007
  Sun Jin Kim authored 2 years ago
  
  825b1007
- evo private stuff · 5351c366
  Max Ramsay King authored 2 years ago
  
  5351c366
- added hsitory recording to evo_learner · 32aeeacd
  Max Ramsay King authored 2 years ago
  
  32aeeacd
- small necesary changes in evo_learner · fd35bf0d
  Sun Jin Kim authored 2 years ago
  
  fd35bf0d
- added the policy-accuracy record · f2e6f159
  Max Ramsay King authored 2 years ago
  
  f2e6f159
Apr 26, 2022
- privatise certain methods in aa_learner's · bd840c0d
  Sun Jin Kim authored 2 years ago
  
  bd840c0d
- add test_exclude_method · bcfdeeec
  Sun Jin Kim authored 2 years ago
  
  bcfdeeec
- revert work on evo_learner · 24808e5a
  Sun Jin Kim authored 2 years ago
  
  24808e5a
- edit evo_learner: · 92b2a3b6
  Sun Jin Kim authored 2 years ago
  
  controller is init'ed inside the learner train_dataset.transform = to.tensor()
  92b2a3b6
- fixed evo learner · 5c322005
  Max Ramsay King authored 2 years ago
  
  5c322005
Apr 25, 2022
- fully implement `exclude_method` in aa_learners · 567998d8
  Sun Jin Kim authored 2 years ago
  
  567998d8
- remove toy_flag parameter from aa_learners · b070fda5
  Sun Jin Kim authored 2 years ago
  
  b070fda5
- finish removing fun_num from aa_learners · c6136f11
  Sun Jin Kim authored 2 years ago
  
  also update tests accordingly
  c6136f11
- FINISH REFACTORING UCB_LEARNER · 839fb15f
  Sun Jin Kim authored 2 years ago
  
  839fb15f
- removed unneeded fun_num from aa_learner · 57953c57
  Max Ramsay King authored 2 years ago
  
  57953c57
- updated aa_learner · dc3ea682
  Max Ramsay King authored 2 years ago
  
  dc3ea682
- updated evo_learner and added exclude_method to aa_learner · 246b6352
  Max Ramsay King authored 2 years ago
  
  246b6352
- continue refactoring ucb · 5ecdfcec
  Sun Jin Kim authored 2 years ago
  
  5ecdfcec
- make /temp_util to temporarily store stuff while refactoring is happening · 5c18be7b
  Sun Jin Kim authored 2 years ago
  
  5c18be7b
- minor changes · 61295621
  Sun Jin Kim authored 2 years ago
  
  61295621
- assimilated ucb_learner into aa_learners · 2e64210a
  Sun Jin Kim authored 2 years ago
  
  2e64210a
- add and change __init__.py's · 6ccb31f8
  Sun Jin Kim authored 2 years ago
  
  6ccb31f8
Apr 24, 2022
- Move and rename ucb1 · 084b2463
  Sun Jin Kim authored 2 years ago
  
  084b2463
- move notebooks into /notebooks · 922f9cf6
  Sun Jin Kim authored 2 years ago
  
  922f9cf6
- removed evo things · 223dfe89
  Max Ramsay King authored 2 years ago
  
  223dfe89
Apr 22, 2022
- fix main.train_cn · 6f3f3748
  Sun Jin Kim authored 2 years ago
  
  6f3f3748
- update aa_learners · 76afa805
  Sun Jin Kim authored 2 years ago
  
  76afa805
Apr 21, 2022
- more stuff · 06ae5603
  Max Ramsay King authored 2 years ago
  
  06ae5603
Apr 20, 2022
- logging info · 5bb0d1c0
  Max Ramsay King authored 2 years ago
  
  5bb0d1c0
- add rs_learner and gru_learner unit tests · 06384f33
  Sun Jin Kim authored 2 years ago
  
  remove gru pickling make main.train_child_netowork robust wrt 0 revise aa_learner tutorial
  06384f33
- Make aa_learner.translate_... robust wrt input size · 363e8919
  Sun Jin Kim authored 2 years ago
  
  363e8919
Apr 19, 2022
- agent generating function · 9f18feed
  Max Ramsay King authored 2 years ago
  
  9f18feed
- change name of func to learn · 9d1e17ff
  Max Ramsay King authored 2 years ago
  
  9d1e17ff
- moved evo learner to aa_learner · c68dc525
  Max Ramsay King authored 2 years ago
  
  c68dc525