https://github.com/openai/baselines

sort by:
Revision Author Date Message Commit Date
a4fba20 remove ref to simple_bench + rank variable not used [mpi gone] 25 October 2017, 21:08:01 UTC
bb40378 change atari preprocessing to use faster opencv some logger changes 25 October 2017, 13:21:29 UTC
4993286 Merge pull request #160 from mkarutz/fixFrameStackingA2C Fixes frame stacking in A2C and ACKTR for multi-channel observations 09 October 2017, 21:12:28 UTC
cc8818f Fixes frame stacking in A2C and ACKTR for multi-channel observation spaces. 09 October 2017, 02:08:41 UTC
3eb71a0 Merge pull request #151 from emansim/master Fixes the NaN issues in ACKTR + bug in run_mujoco.py 30 September 2017, 21:51:56 UTC
f8663ea fixes acktr_cont issues 30 September 2017, 21:21:04 UTC
699919f Merge pull request #64 from jhumplik/master Use standardized advantages in trpo. 07 September 2017, 08:57:04 UTC
498b4cf Merge pull request #128 from louiehelm/louiehelm-patch-1 Fix command lines 06 September 2017, 08:04:47 UTC
5893874 fix ppo command in readme 05 September 2017, 13:06:19 UTC
3d3ea6c fix trpo command in readme 05 September 2017, 13:04:37 UTC
902ffcb Merge pull request #120 from hamzamerzic/tensorflow_global_variable Deprecated VARIABLES -> GLOBAL_VARIABLES. 29 August 2017, 04:27:23 UTC
a7320b8 Deprecated VARIABLES -> GLOBAL_VARIABLES. 28 August 2017, 14:51:48 UTC
4e2a570 Merge pull request #104 from stevenschmatz/patch-1 Fix relative links in README.md 28 August 2017, 05:54:52 UTC
6f39148 fix gym req 28 August 2017, 05:49:50 UTC
2f30833 Merge branch 'master' of github.com:openai/baselines 28 August 2017, 05:36:44 UTC
00cdeff add __init__.py 28 August 2017, 05:36:24 UTC
410ef38 Merge pull request #103 from learnercys/master Adding links to source files 28 August 2017, 05:31:46 UTC
aa6e58b fix readmes 28 August 2017, 05:22:14 UTC
d9f194f Fix atari wrapper (affecting a2c perf) and pposgd mujoco performance - removed vf clipping in pposgd - that was severely degrading performance on mujoco because it didn’t account for scale of returns - switched adam epsilon in pposgd_simple - brought back no-ops in atari wrapper (oops) - added readmes - revamped run_X_benchmark scripts to have standard form - cleaned up DDPG a little, removed deprecated SimpleMonitor and non-idiomatic usage of logger 28 August 2017, 05:14:59 UTC
06b071c Fix relative links in README.md 18 August 2017, 17:35:22 UTC
3f676f7 ACKTR + A2C 18 August 2017, 16:25:39 UTC
b7966b3 Adding links to source files 18 August 2017, 07:16:00 UTC
8822518 Parameter space noise for DQN and DDPG (#75) * Export param noise * Update documentation * Final finishing touches 27 July 2017, 15:10:59 UTC
4862140 Use standardized advantages in trpo. 23 July 2017, 20:42:55 UTC
df82a15 Fix broken links in DQN readme 23 July 2017, 16:58:10 UTC
5dc0062 readme fiddling 20 July 2017, 16:00:24 UTC
79b4a8a Merge pull request #60 from openai/ppo-trpo ppo and trpo 20 July 2017, 15:55:43 UTC
da99706 ppo and trpo 20 July 2017, 15:52:35 UTC
80f94f8 bump version 12 July 2017, 21:48:05 UTC
2b1b437 Update simple.py 12 July 2017, 21:42:36 UTC
04cd0dc Merge pull request #52 from farbeiza/patch-1 Effectively apply weights from the replay buffer 12 July 2017, 21:37:28 UTC
248aad1 Merge pull request #39 from mirceamironenco/master Fix TF graph variables deprecation 12 July 2017, 21:32:24 UTC
d76cd12 Effectively apply weights from the replay buffer It seems that the weights retrieved from the replay buffer are not applied when training the model. Is there any reason for that or am I missing something? In any case, I have added a parameter in order for them to be used; just in case it is useful. 11 July 2017, 09:09:51 UTC
91b1085 Fixed TF graph variables deprecation 28 June 2017, 13:48:45 UTC
0778e9f Merge pull request #28 from zach-nervana/patch-1 remove unnecessary initialization of variable resized_screen 24 June 2017, 00:05:25 UTC
59c7887 Merge pull request #26 from LinZichuan/master Update setup.py 24 June 2017, 00:02:05 UTC
3d235ae Merge pull request #33 from cxxgtxy/master Fix README since BreakOut pretrained model doesn't match the correct … 23 June 2017, 23:59:55 UTC
5e73387 Fix README since BreakOut pretrained model doesn't match the correct tensor shape. Therefore, Pong is used instead. 16 June 2017, 07:38:42 UTC
ec38bf4 remove unnecessary initialization of variable resized_screen 09 June 2017, 12:53:10 UTC
ef1a240 Update setup.py 07 June 2017, 09:29:38 UTC
184440f Merge pull request #22 from ngc92/doc_fixes docstring and comment fixes 04 June 2017, 07:41:34 UTC
fba0ac3 Merge pull request #15 from tiagosgc/patch-1 Update README.md 04 June 2017, 07:40:58 UTC
584261a Merge pull request #14 from quanvuong/master Consistent initial type (float) for episode_rewards 04 June 2017, 07:40:42 UTC
9c10c2f Merge pull request #13 from ppwwyyxx/patch-1 Update setup.py 04 June 2017, 07:40:31 UTC
0291948 docstring and comment fixes 01 June 2017, 23:43:51 UTC
1f3c3e3 Update README.md 31 May 2017, 11:14:28 UTC
86054f7 Consistent initial type (float) for episode_rewards 30 May 2017, 03:49:25 UTC
709c327 Update setup.py `PongNoFrameskip-v4` seems to require `gym>=0.9.1` 30 May 2017, 02:39:25 UTC
fc2bbed Merge pull request #11 from yenchenlin/fix-typo Fix typos 28 May 2017, 19:56:46 UTC
4fd1d21 Fix typo 28 May 2017, 17:13:47 UTC
5c80997 Merge pull request #9 from AAorris/patch-1 tf_util: spelling / docstring updates 26 May 2017, 23:24:57 UTC
2361220 tf_util: spelling / docstring updates 26 May 2017, 05:53:09 UTC
7327a15 update Atari envs to v4 and warn Python 2 users. 25 May 2017, 21:53:29 UTC
0071b85 Merge pull request #2 from omoindrot/patch-1 Correct path to script "download_model" 24 May 2017, 21:55:54 UTC
d2c51f5 Correct path to script "download_model" `python -m baselines.deepq.experiments.download_model` becomes `python -m baselines.deepq.experiments.atari.download_model` 24 May 2017, 20:13:30 UTC
958810e Initial commit 24 May 2017, 09:34:20 UTC
back to top