248 Commits

Author SHA1 Message Date
Trinkle23897
5f2f05a570 fix #40 2020-06-13 17:06:08 +08:00
Trinkle23897
1a914336f7 add random action in collector (fix #78) 2020-06-11 08:57:37 +08:00
Trinkle23897
397e92b0fc fix #77 2020-06-10 12:06:56 +08:00
Trinkle23897
f1951780ab fix a bug of storing batch over batch data into buffer 2020-06-09 18:46:14 +08:00
Trinkle23897
513573ea82 add link 2020-06-08 22:20:52 +08:00
Trinkle23897
560116d0b2 cheat sheet 2020-06-08 21:53:00 +08:00
Alexis DUBURCQ
52be533d06
Enable getattr for SubprocVecEnv. (#74)
* Enable getattr for SubprovVecEnv.

* Consistent API between VectorEnv and SubprocVecEnv.

* Avoid code duplication. Add unit tests.

* Add docstring.

* Test more branches.

* Fix UT.

Co-authored-by: Alexis Duburcq <alexis.duburcq@wandercraft.eu>
2020-06-05 17:17:43 +08:00
Alexis DUBURCQ
66be5641b6
Fix to_numpy. (#73)
Co-authored-by: Alexis Duburcq <alexis.duburcq@wandercraft.eu>
2020-06-04 22:32:05 +08:00
Trinkle23897
dc451dfe88 nstep all (fix #51) 2020-06-03 13:59:47 +08:00
Trinkle23897
ff81a18f42 compute_nstep_returns (item 2 of #51) 2020-06-02 22:29:50 +08:00
Trinkle23897
5f2c5347df v0.2.3 2020-06-01 09:37:30 +08:00
Trinkle23897
ba1b3e54eb fix #69 2020-06-01 08:30:09 +08:00
Alexis DUBURCQ
1fce527c77
Fix 'to_tensor' dtype/device forwarding for Batch over Batch. (#68)
* Fix Batch to_torch method not updating dtype/device of already converted data.

* Fix dtype/device to forwarded by to_tensor for Batch over Batch.

* Add Unit test to check to_torch dtype/device recursive forwarding.

* Batch UT check accessing data using both dict and class style.

* Fix utils to_tensor dtype/device forwarding. Add Unit tests.

* Fix UT.

Co-authored-by: Alexis Duburcq <alexis.duburcq@wandercraft.eu>
Co-authored-by: n+e <463003665@qq.com>
2020-05-30 21:40:31 +08:00
Alexis DUBURCQ
529a4cf44c
Add pickle support for Batch. Fix VectorEnv. (#67)
* Fix vecenv.

* Add pickle support for Batch class.

* Add Batch pickle Unit Test.

* Fix lint.

* Swap Batch UT.

* Fix lint.

Co-authored-by: Alexis Duburcq <alexis.duburcq@wandercraft.eu>
2020-05-30 21:29:33 +08:00
Alexis DUBURCQ
dd3e2130bb
Infer the right dtype for replay buffers. (#64) 2020-05-29 22:27:03 +08:00
Alexis DUBURCQ
8af7196a9a
Robust conversion from/to numpy/pytorch (#63)
* Enable to convert Batch data back to torch.

* Add torch converter to collector.

* Fix

* Move to_numpy/to_torch convert in dedicated utils.py.

* Use to_numpy/to_torch to convert arrays.

* fix lint

* fix

* Add unit test to check Batch from/to numpy.

* Fix Batch over Batch.

Co-authored-by: Alexis Duburcq <alexis.duburcq@wandercraft.eu>
2020-05-29 20:45:21 +08:00
Alexis DUBURCQ
b5093ecb56
Minor refactor for Batch class. (#61)
* Minor refactor for Batch class.

* Fix.

* Add back key sorting.

Co-authored-by: Alexis Duburcq <alexis.duburcq@wandercraft.eu>
2020-05-29 17:56:46 +08:00
Trinkle23897
be9ce44290 fix #59 2020-05-29 11:49:47 +08:00
Trinkle23897
d2b2fa87c0 fix #56 2020-05-29 08:03:37 +08:00
Trinkle23897
de556fd22d item3 of #51 2020-05-27 11:02:23 +08:00
magicly
6237cc0d52
fix dqn zero eps (#52)
Co-authored-by: liyan <liyan1@digisky.com>
2020-05-21 11:35:41 +08:00
Imone
57bca16f94
Fix log_prob and PPO dual_clip (#49)
* Added DiagGaussian to fix log_probg

* Disable PPO dual_clip
2020-05-18 16:23:35 +08:00
Trinkle23897
0eef0ca198 fix optional type syntax 2020-05-16 20:08:32 +08:00
Trinkle23897
9b26137cd2 add type annotation 2020-05-12 11:31:47 +08:00
Trinkle23897
075825325e add preprocess_fn (#42) 2020-05-05 13:39:51 +08:00
Trinkle23897
04b091d975 fix max-grad-norm err in a2c (#46) 2020-05-04 12:33:04 +08:00
Trinkle23897
c2a7caf806 add recurrent actor and critic 2020-04-30 16:31:40 +08:00
Trinkle23897
134f787e24 reserve 'policy' keyword in replay buffer 2020-04-29 17:48:48 +08:00
Trinkle23897
bb2f833d0e support Batch of Batch and fix bugs (#38) 2020-04-29 12:14:53 +08:00
nicoguertler
8f718d9b13
Fix log_prob in SAC (#41) 2020-04-28 23:44:15 +08:00
Trinkle23897
80d661907e Multimodal obs (#38, #27, #25) 2020-04-28 20:56:02 +08:00
Trinkle23897
959955fa2a fix historical issues 2020-04-26 16:13:51 +08:00
Trinkle23897
6b96f124ae fix pdqn 2020-04-26 15:11:20 +08:00
rocknamx
b23749463e
Prioritized DQN (#30)
* add sum_tree.py

* add prioritized replay buffer

* del sum_tree.py

* fix some format issues

* fix weight_update bug

* simply replace replaybuffer in test_dqn without weight update

* weight default set to 1

* fix sampling bug when buffer is not full

* rename parameter

* fix formula error, add accuracy check

* add PrioritizedDQN test

* add test_pdqn.py

* add update_weight() doc

* add ref of prio dqn in readme.md and index.rst

* restore test_dqn.py, fix args of test_pdqn.py
2020-04-26 12:05:58 +08:00
Trinkle23897
70290346ea compatible with torch==1.5.0 (fix #37) 2020-04-26 11:04:45 +08:00
Trinkle23897
8812eaa502 fix #36 2020-04-23 22:06:18 +08:00
Minghao Zhang
205698dd66
fix #33 (#34) 2020-04-21 15:36:08 +08:00
Trinkle23897
4fd826761c enable null buffer in test collector 2020-04-20 11:50:18 +08:00
Trinkle23897
815f3522bb imitation with discrete action space 2020-04-20 11:25:20 +08:00
Trinkle23897
6bf1ea644d fix ppo 2020-04-19 14:30:42 +08:00
Trinkle23897
680fc0ffbe gae 2020-04-14 21:11:06 +08:00
Trinkle23897
7b65d43394 vanilla imitation learning 2020-04-13 19:37:27 +08:00
Trinkle23897
6a244d1fbb save_fn 2020-04-11 16:54:27 +08:00
Trinkle23897
74407e13da env info log_fn (#28) 2020-04-10 18:02:05 +08:00
Trinkle23897
ecfcb9f295 fix docs 2020-04-10 11:16:33 +08:00
Trinkle23897
3cc22b7c0c __call__ -> forward 2020-04-10 10:47:16 +08:00
Trinkle23897
13086b7f64 add ignore_obs_next in buffer 2020-04-10 09:01:17 +08:00
Trinkle23897
19f2cce294 seealso and change policy dir structure 2020-04-09 21:36:53 +08:00
Trinkle23897
6da80e045a fix rnn (#19), add __repr__, and fix #26 2020-04-09 19:53:45 +08:00
Trinkle23897
86572c66d4 maybe finished rnn? 2020-04-08 21:13:15 +08:00