Commit Graph

Select branches

Hide Pull Requests

aray-extra-imports

fix998

fix_build

fix_monitor_close

games/master

gdb

her-fixes

internal

like_pr_787

master

matthias-her

observation-dtype

old_acktr_cont

param-noise-release

peterz_383

peterz_alex_propagate_vecenv_changes

peterz_benchmarks

peterz_codecov_report

peterz_flatten_dict_wrapper

peterz_import_internal

peterz_import_internal_2e3a166

peterz_learn_registration

peterz_mpiless

peterz_pr_214

peterz_test_benchmarks

peterz_tflstm

peterz_tflstm_1

peterz_tflstm_with_ppo2

peterz_ubuntu18_04

peterz_update_READMEs

peterz_viz

ppo-trpo

simple_bench_mpi_cleanup

stateful_rnn

tf2

tuple_pdtype

#1000

#1002

#1003

#1003

#1010

#1011

#1012

#1014

#1015

#1016

#1021

#1021

#1022

#1022

#1027

#1028

#1029

#103

#1032

#1034

#1037

#1037

#104

#1053

#1053

#1056

#1056

#1057

#1057

#1062

#1062

#1066

#1067

#1067

#107

#1076

#1077

#1077

#1079

#1079

#1089

#1089

#1093

#11

#1106

#1106

#1108

#113

#113

#1137

#1137

#1138

#1139

#1139

#1143

#1143

#1144

#1144

#1146

#1146

#1147

#1155

#1155

#1160

#1167

#1167

#1173

#1173

#1174

#1174

#1175

#1175

#1176

#1176

#1177

#1177

#1178

#1178

#1179

#1179

#1180

#1180

#1181

#1181

#1182

#1182

#1183

#1183

#1184

#1184

#1185

#1185

#1186

#1186

#1187

#1187

#1188

#1188

#119

#1191

#1193

#1193

#120

#1201

#1201

#122

#122

#124

#128

#129

#129

#13

#132

#133

#133

#138

#138

#14

#141

#141

#143

#143

#15

#150

#150

#151

#153

#153

#154

#156

#158

#158

#160

#161

#163

#163

#169

#169

#174

#174

#178

#178

#181

#181

#191

#193

#194

#199

#2

#205

#207

#207

#213

#213

#214

#215

#216

#216

#218

#218

#219

#219

#22

#221

#223

#223

#226

#229

#23

#23

#230

#231

#231

#233

#233

#251

#251

#254

#255

#255

#259

#26

#260

#261

#261

#265

#268

#271

#273

#28

#281

#282

#282

#283

#283

#287

#289

#290

#293

#297

#299

#30

#30

#306

#308

#312

#312

#313

#313

#319

#32

#32

#322

#328

#328

#33

#330

#330

#333

#333

#337

#337

#34

#34

#348

#348

#349

#352

#352

#363

#363

#369

#375

#375

#376

#376

#377

#385

#388

#389

#39

#396

#401

#401

#407

#409

#412

#412

#416

#418

#422

#424

#424

#425

#425

#427

#430

#437

#437

#438

#438

#439

#444

#444

#447

#457

#457

#459

#459

#461

#464

#474

#481

#481

#488

#488

#49

#49

#490

#491

#498

#498

#499

#499

#50

#50

#502

#503

#507

#508

#513

#513

#514

#516

#516

#52

#527

#529

#529

#533

#534

#535

#537

#539

#542

#547

#547

#554

#556

#558

#56

#560

#561

#561

#562

#565

#567

#567

#569

#570

#570

#571

#571

#574

#578

#581

#585

#588

#595

#598

#599

#599

#6

#6

#60

#605

#605

#607

#609

#612

#614

#616

#616

#620

#620

#63

#632

#635

#636

#64

#643

#653

#654

#655

#661

#664

#665

#666

#669

#671

#674

#675

#676

#677

#679

#680

#682

#683

#684

#685

#689

#69

#69

#694

#701

#702

#703

#704

#705

#707

#712

#712

#715

#715

#716

#72

#72

#722

#725

#725

#728

#73

#73

#732

#733

#734

#735

#740

#744

#745

#75

#751

#752

#763

#767

#777

#779

#781

#784

#785

#787

#789

#789

#793

#796

#797

#800

#806

#807

#812

#813

#817

#817

#819

#820

#823

#824

#826

#833

#836

#841

#847

#848

#849

#854

#856

#859

#86

#86

#860

#863

#864

#865

#866

#867

#870

#870

#871

#875

#877

#877

#879

#885

#886

#891

#895

#898

#898

#899

#9

#905

#906

#907

#908

#911

#912

#914

#914

#915

#917

#920

#921

#930

#931

#931

#932

#932

#933

#937

#937

#946

#95

#950

#952

#952

#955

#955

#958

#958

#96

#96

#964

#964

#968

#970

#976

#978

#984

#990

#995

#997

Mono Color

• 5c62f5c7dd added peterz to baselines authorlist Peter Zhokhov 2018-09-11 12:44:51 -07:00
• c5d6f2996c Merge branch 'master' of github.com:openai/baselines Peter Zhokhov 2018-09-11 12:40:29 -07:00
• 29bf587d15 Merge branch 'master' of github.com:openai/baselines Peter Zhokhov 2018-09-11 12:40:29 -07:00
• 06bdc2860c docstrings about vecenvs Peter Zhokhov 2018-09-11 12:40:23 -07:00
• 23b2333238 baselines issue #564 (#574) pzhokhov 2018-09-10 11:50:59 -07:00
• adaa8aefa8 baselines issue #564 (#574) pzhokhov 2018-09-10 11:50:59 -07:00
• 8614c4ddbf flake8 Peter Zhokhov 2018-09-10 10:41:29 -07:00
• 59a7ffb84d fixe tests of test_env_after_learn Peter Zhokhov 2018-09-10 10:32:42 -07:00
• 58b1021b28 Add tensorboard start command for convenience (#569) Daniel Angelov 2018-09-08 01:04:02 +01:00
• a60e88bff9 git subrepo pull (merge) baselines Peter Zhokhov 2018-09-07 14:42:29 -07:00
• 75b93b890e implement pdfromlatent in BernoulliPdType (#81) pzhokhov 2018-09-06 16:17:59 -07:00
• 565b2153d7 Add lots of docstrings (#76) John Schulman 2018-09-07 07:31:30 +09:00
• 35e95ee85a fix python 3.5 string format compatibility Peter Zhokhov 2018-09-06 12:00:19 -07:00
• ad219e205d VecNormalize: set env. returns to zero on resets. (#556) Isaac Lascasas 2018-09-06 19:21:50 +02:00
• be9118bcd8 git subrepo pull (merge) baselines Peter Zhokhov 2018-09-06 10:17:55 -07:00
• 02a5e7aed5 fixes to readme and baselines/run.py (#80) pzhokhov 2018-09-06 10:17:21 -07:00
• 87ac8bc317 install roboschool in install.py (#55) pzhokhov 2018-09-05 14:03:13 -07:00
• cc4215ef4b refactor common.models via registering reflection (#565) Tom 2018-09-07 01:16:06 +08:00
• 1e9051e87e fixed warning (#464) Clayton Thorrez 2018-09-05 18:12:01 -04:00
• 43ed76944b Fix mean reward per episode after training Pong. (#562) uronce-cc 2018-09-06 06:06:29 +08:00
• 7f08c675bb git subrepo pull (merge) baselines Peter Zhokhov 2018-09-04 10:23:29 -07:00
• b3f966aa02 use env.render in dummy_vec_env.render when num_envs == 1 (#74) pzhokhov 2018-09-04 10:22:32 -07:00
• 51cefc933b make load_variables compatible with old list format (#71) pzhokhov 2018-08-30 15:32:55 -07:00
• 7bccb2969f baselines: default logger similar to configure() logger, rcall: don't call logger.configure() for new rl_algs Christopher Hesse 2018-08-30 15:04:40 -07:00
• 0a40206c6c ncpu needs to be an integer. (#558) old_acktr_cont uronce-cc 2018-09-01 00:02:18 +08:00
• 1937826784 Fix alien syntax and apply PEP 8 style (#554) Alfredo Canziani 2018-08-30 20:21:25 -04:00
• b29c8020d7 remove saving model as a pickle file in ppo2 (tries to pull environment in; bad idea - may need to use constructor argument pickling or somesuch if at all necessary) (#69) pzhokhov 2018-08-30 13:40:40 -07:00
• 4ec308aaa4 fixed syntax Peter Zhokhov 2018-08-30 10:27:18 -07:00
• 3bbf3f3511 allow_early_resets=True in create_vec_env Peter Zhokhov 2018-08-30 09:40:42 -07:00
• e5de29a954 instructions for tensorboard (#61) Joshua Meier 2018-08-29 15:25:47 -07:00
• 2507d335f9 Tensorboard util (#60) Joshua Meier 2018-08-29 15:17:43 -07:00
• bdd4d385a6 Fix result_plotters in vectorized mujoco environments (#533) Damien Lancry 2018-08-29 01:48:56 +01:00
• 0961f5dd94 git subrepo pull (merge) baselines Peter Zhokhov 2018-08-27 16:39:51 -07:00
• 337d913a8f remove reset_task from subproc vec env (#45) Christopher Hesse 2018-08-27 12:48:05 -07:00
• 34af61a132 baselines: fix dummy vec env render mode (#42) Karl Cobbe 2018-08-26 20:54:38 -07:00
• 1ea5ec647c export SimpleEnv and assert_envs_equal, fix minor bug in action space (#46) Christopher Hesse 2018-08-24 15:44:56 -07:00
• 2fc7a1cbee Trigger benchmarks from buildkite (#40) pzhokhov 2018-08-23 13:20:01 -07:00
• 14c1d69ef4 Reduce duplication in VecEnv subclasses. (#38) John Schulman 2018-08-22 13:54:34 -07:00
• c8f6d8bac7 address rl-algs issue #169 (missing util functions from rcall) (#30) pzhokhov 2018-08-21 20:51:09 -07:00
• 3a006ba50e flake8 fixes (#35) pzhokhov 2018-08-21 17:41:25 -07:00
• c6c0f45cb1 fix 'async' is a reserved word in Python >= 3.7 (#495) (#542) Tom 2018-08-28 03:36:43 +08:00
• e92a6ad8f4 Update README.md (#537) wangjksjtu 2018-08-28 03:35:48 +08:00
• 92b9a37257 Updated example commands to run ppo2 (#534) HelgeS 2018-08-24 00:58:27 +02:00
• cb14da96ca Fix typo on policies documentation (#535) Armin Primadi 2018-08-24 05:56:13 +07:00
• 3900f2a447 baselines issue 146 (remove tensorflow from setup.py) (#34) pzhokhov 2018-08-21 16:51:37 -07:00
• 20d22a5d79 Fix baselines build (fails due to lack of mujoco in public baselines container) (#29) pzhokhov 2018-08-20 19:15:17 -07:00
• caf7b08b4d Baselines issue #525 (lack of docs for recurrent policies) (#27) pzhokhov 2018-08-20 13:54:56 -07:00
• ca0165cdf5 flake8 complaints Peter Zhokhov 2018-08-17 18:09:13 -07:00
• eb5b605f86 restore subrepo conftest.py files (#22) pzhokhov 2018-08-17 17:01:40 -07:00
• a89bee3c8d Merge commit 'refs/subrepo/baselines/fetch' into subrepo/baselines Peter Zhokhov 2018-08-17 13:55:27 -07:00
• 353bb15e90 deduplicate algorithms in rl-algs and baselines (#18) pzhokhov 2018-08-17 09:40:35 -07:00
• 64c0c0a043 Setup travis (#12) pzhokhov 2018-08-15 10:34:38 -07:00
• 5fee99e771 Setup travis (#12) pzhokhov 2018-08-15 10:34:38 -07:00
• 5edcd6886e Fix argument error in deepq (#508) Youngjin Kim 2018-08-17 06:55:57 +09:00
• bcde04e710 Fix argument error in deepq (#508) games/master Youngjin Kim 2018-08-17 06:55:57 +09:00
• cd375ab209 update readmes (#514) pzhokhov 2018-08-16 14:53:49 -07:00
• 5622a09fa4 update readmes (#514) pzhokhov 2018-08-16 14:53:49 -07:00
• 0f8d640554 updated README files and deepq.train_cartpole example peterz_update_READMEs Peter Zhokhov 2018-08-16 13:15:51 -07:00
• 44b91f3454 Merge branch 'master' of github.com:openai/baselines into peterz_update_READMEs Peter Zhokhov 2018-08-16 12:26:51 -07:00
• 0c2a6936c4 adding a link to repo-wide README Peter Zhokhov 2018-08-16 12:23:06 -07:00
• 2614f0f65a update per-algorithm READMEs to reflect new way of running algorithms Peter Zhokhov 2018-08-16 12:18:06 -07:00
• e2da7cd42f Several bugfixes for #504, #505, #506 related to Classic Control and deepq (#507) Pim de Haan 2018-08-16 12:08:53 -07:00
• 0f281fd0ca flake8 complaint peterz_alex_propagate_vecenv_changes Peter Zhokhov 2018-08-15 10:31:34 -07:00
• ef4146005a propagate Alex's changes to vecenv module (needs to be done manually until baselines is removed from rl-algs) Peter Zhokhov 2018-08-15 10:26:44 -07:00
• 11176eedce tests on ubuntu18.04 peterz_ubuntu18_04 Peter Zhokhov 2018-08-14 16:43:13 -07:00
• b222dd0610 updated links in README to point to master Peter Zhokhov 2018-08-13 16:01:24 -07:00
• 1870685071 Publish benchmark results (#502) pzhokhov 2018-08-13 15:59:43 -07:00
• 841da92f4d add code coverage report peterz_codecov_report Peter Zhokhov 2018-08-13 10:44:49 -07:00
• 8c2aea2add refactor a2c, acer, acktr, ppo2, deepq, and trpo_mpi (#490) pzhokhov 2018-08-13 09:56:44 -07:00
• 624231827c merged benchmarks branch Peter Zhokhov 2018-08-13 09:28:10 -07:00
• b650cd862e lstm network builders using tf lstm peterz_tflstm_1 Peter Zhokhov 2018-08-10 14:24:55 -07:00
• dbcc4e0252 lstm network builders using tf lstm peterz_tflstm Peter Zhokhov 2018-08-10 14:23:45 -07:00
• 2ebdc28791 lstm network builders using tf lstm peterz_tflstm_with_ppo2 Peter Zhokhov 2018-08-10 14:21:30 -07:00
• 217b111c88 merged refactor Peter Zhokhov 2018-08-10 14:14:46 -07:00
• ea68f3b7e6 dummy commit to RUN BENCHMARKS peterz_benchmarks Peter Zhokhov 2018-08-10 09:46:43 -07:00
• ca721a4be6 Merge branch 'observation-dtype' of github.com:openai/baselines into peterz_benchmarks Peter Zhokhov 2018-08-10 09:45:50 -07:00
• 72f3572a10 fixed syntax in conv_only RUN BENCHMARKS Peter Zhokhov 2018-08-08 16:24:39 -07:00
• b9cd941471 dummy commit to RUN BENCHMARKS Peter Zhokhov 2018-08-08 15:59:59 -07:00
• 0899b71ede scale the images in conv_only RUN BENCHMARKS Peter Zhokhov 2018-08-08 15:15:03 -07:00
• cc8c9541fb dummy commit to RUN BENCHMARKS Peter Zhokhov 2018-08-08 15:10:39 -07:00
• cb32522394 enable all benchmarks Peter Zhokhov 2018-08-08 15:10:00 -07:00
• 1e40ec22be dummy commit to RUN BENCHMARKS Peter Zhokhov 2018-08-08 10:45:18 -07:00
• 701a36cdfa added a note in README about TfRunningMeanStd and serialization of VecNormalize Peter Zhokhov 2018-08-08 10:44:58 -07:00
• 366f486e34 Update README.md (#416) Tony Yu Cao 2018-08-08 18:42:10 +01:00
• 5a7f9847d8 flake8 complaints Peter Zhokhov 2018-08-03 13:59:58 -07:00
• b63134e5c5 added acer runner (missing import) Peter Zhokhov 2018-08-03 13:31:37 -07:00
• db314cdeda Merge branch 'peterz_profile_vec_normalize' into peterz_migrate_rlalgs Peter Zhokhov 2018-08-03 11:47:36 -07:00
• b08c083d91 use VecNormalize with regular RunningMeanStd Peter Zhokhov 2018-08-03 11:44:12 -07:00
• bfbbe66d9e profiling wip Peter Zhokhov 2018-08-02 11:23:12 -07:00
• 1c5c6563b7 reverted VecNormalize to use RunningMeanStd (no tf) Peter Zhokhov 2018-08-02 10:55:09 -07:00
• 1fa8c58da5 reverted VecNormalize to use RunningMeanStd (no tf) Peter Zhokhov 2018-08-02 10:54:07 -07:00
• f6d1115ead reverted running_mean_std to user property decorators for mean, var, count Peter Zhokhov 2018-08-02 10:32:22 -07:00
• f6d5a47bed use ncpu=1 for mujoco sessions - gives a bit of a performance speedup Peter Zhokhov 2018-08-02 10:24:21 -07:00
• c2df27bee4 non-tf normalization benchmark RUN BENCHMARKS Peter Zhokhov 2018-08-02 09:41:41 -07:00
• 974c15756e changed default ppo2 lr schedule to linear RUN BENCHMARKS Peter Zhokhov 2018-08-01 16:24:44 -07:00
• ad43fd9a35 add defaults Peter Zhokhov 2018-08-01 16:15:59 -07:00
• 72c357c638 hardcode names of retro environments Peter Zhokhov 2018-08-01 15:18:59 -07:00
• e00e5ca016 run ppo_mpi benchmarks only RUN BENCHMARKS Peter Zhokhov 2018-08-01 14:56:08 -07:00
• 705797f2f0 Merge branch 'peterz_migrate_rlalgs' into peterz_benchmarks Peter Zhokhov 2018-08-01 14:46:40 -07:00
• fcd84aa831 make_atari_env compatible with mpi Peter Zhokhov 2018-08-01 14:46:18 -07:00