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

• 7446e6ea34 fix typo fix_monitor_close Peter Zhokhov 2020-01-31 05:23:33 -08:00
• 3bd068c82c actually close the file with the results on Monitor.close() Peter Zhokhov 2020-01-31 05:09:29 -08:00
• ea25b9e8b2 Monitor should close what it inherits (#1076) master Harry Uglow 2020-01-31 13:06:18 +00:00
• 9ee399f5b2 Fix build with latest gym (#1034) pzhokhov 2019-11-10 11:10:01 -08:00
• 8d9e20fec3 narrow down gym version to 0.15.4 <= gym < 0.16.0 fix_build Peter Zhokhov 2019-11-10 11:08:59 -08:00
• fc23c78c77 fix imports Peter Zhokhov 2019-11-08 15:39:57 -08:00
• 25f750d84f update to use latest version of gym Peter Zhokhov 2019-11-08 15:31:40 -08:00
• 391811d98c SubprocVecEnv uses CloudpickleWrapper to send specs (#1028) Tomasz Wrona 2019-11-09 00:23:49 +01:00
• b99a73afe3 entrypoint variable made public (#970) and Fix RuntimeError (#910) (#1015) (#1032) tf2 SOLARIS 2019-11-09 08:20:54 +09:00
• 517433f22a flake8 complaints Peter Zhokhov 2019-11-08 15:15:38 -08:00
• 713f1a0aec tf2: Updated setup.py dependencies. (#1002) Isaac Lascasas 2019-10-26 00:50:04 +02:00
• 665b888eeb Fix behavior cloning due to API changes (#1014) Yen-Chen Lin 2019-10-25 18:44:43 -04:00
• f40a477a17 fix tf2 branch name Christopher Hesse 2019-10-25 15:27:30 -07:00
• c6144bdb6a Fix RuntimeError (#910) (#1015) johannespitz 2019-10-26 00:24:41 +02:00
• adba88b218 add quote marks to tensorflow < 2 to avoid bash logic Peter Zhokhov 2019-10-11 17:13:43 -07:00
• bfbc3bae14 update status, fix the tensorflow version in the build Peter Zhokhov 2019-10-11 15:23:14 -07:00
• f703776c91 fix a bug in acer saving and loading model (#990) Haiyang Chen 2019-09-27 23:39:41 +01:00
• 53797293e5 use allreduce instead of Allreduce (send pickled data instead of floats) - probably affects performance somewhat, but avoid element number mismatch. Fixes 998 (#1000) pzhokhov 2019-09-27 14:45:31 -07:00
• 0e423a0108 use allreduce instead of Allreduce (send pickled data instead of floats) - probably affects performance somewhat, but avoid element number mismatch. Fixes 998 fix998 Peter Zhokhov 2019-09-06 14:36:35 -07:00
• 229a772b81 Release notes for Tensorflow 2.0 support. (#997) tanzhenyu 2019-08-29 14:25:44 -07:00
• d80b075904 Make SubprocVecEnv works with DummyVecEnv (#908) Tomasz Wrona 2019-08-29 21:16:25 +02:00
• d1a05a0dd2 Baselines for Tensorflow 2.0. (#978) tanzhenyu 2019-08-08 11:03:17 -07:00
• 0182fe1877 entrypoint variable made public (#970) NicoBach 2019-08-06 01:03:19 +02:00
• 1fb4dfb780 Fix typo in GAIL dataset log (#950) Seungjae Ryan Lee 2019-08-06 08:02:43 +09:00
• 7cadef715f Fix typo (#930) Timo Kaufmann 2019-08-06 01:02:21 +02:00
• fce4370ba2 Remove duplicate code in adaptive param noise. (#976) tanzhenyu 2019-08-05 16:01:54 -07:00
• c57528573e Remove model def from deepq. (#946) tanzhenyu 2019-06-27 10:12:38 -07:00
• 2bca7901f5 Updating the version to 0.1.6 (#933) Marcin Michalski 2019-06-24 19:19:01 +02:00
• ba2b017820 add log_path flag to command line utility (#917) albert 2019-06-07 15:05:52 -07:00
• 7c520852d9 Fix converting list of LazyFrames to ndarray (#907) Anton Grigoryev 2019-06-01 02:49:46 +03:00
• 1c872ca8fd run test_monitor through pytest; fix the test, add flake8 to bench direectory - like PR 891 (#921) pzhokhov 2019-05-31 15:36:20 -07:00
• ff8d36a7a7 Starting to reassign waiting_step in shmem_vecenv (#915) Jinho Lee 2019-06-01 06:31:35 +09:00
• 7614b02f7a remove f strings for python back compatibility (#906) Sridhar Thiagarajan 2019-05-31 14:27:11 -07:00
• f7d5a265e1 suppress excessive messages from unused loggers (#920) Andy Twigg 2019-05-31 14:26:45 -07:00
• 21776e8f57 Support Tuple observation spaces (#911) Joshua Meier 2019-05-31 17:06:20 -04:00
• 401a89e515 add tuple pdtype tuple_pdtype Jonathan Raiman 2019-05-23 15:43:48 -07:00
• 9b68103b73 release Internal changes (#895) pzhokhov 2019-05-08 11:36:10 -07:00
• 1ab9fae0b5 test fixes internal Peter Zhokhov 2019-05-03 16:36:03 -07:00
• 75200671c4 fix tests - add matplotlib to setup_requires, put mpi4py import in try-except Peter Zhokhov 2019-05-03 16:29:10 -07:00
• 46fa1b6453 merge master Peter Zhokhov 2019-05-03 15:57:31 -07:00
• a1a9bd6174 Merge branch 'internal' of github.com:openai/baselines into internal Peter Zhokhov 2019-05-03 15:56:04 -07:00
• ef7ac116cb (onp, np) -> (np, jp), switch jax code to use mark_slow decorator (#363) John Schulman 2019-04-26 17:42:43 -07:00
• 1fa6ac38f1 JRL PPO test with delayed identity env (#355) pzhokhov 2019-04-24 17:04:36 -07:00
• 07536451ee Procgen fixes (#352) Karl Cobbe 2019-04-23 16:33:30 -07:00
• 64dfabb8eb Add initializer for process-level setup in SubprocVecEnv (#276) Greg Brockman 2019-04-23 13:40:08 -07:00
• f5daca8c22 delete unnecessary stuff (#338) John Schulman 2019-04-22 14:45:01 -07:00
• 8e0282ee94 ci/runtests.sh - pass all folders to pytest (#342) pzhokhov 2019-04-22 14:41:46 -07:00
• ddcab1606d Procgen Benchmark Updates (#328) Karl Cobbe 2019-04-22 13:12:45 -07:00
• bc4eef6053 fix tests (#335) Christopher Hesse 2019-04-20 15:06:18 -07:00
• 967fc8c37f Fixed sequence env minor (#333) John Schulman 2019-04-20 10:08:09 -07:00
• a93dde3b2b extra functionality in baselines.common.plot_util (#310) pzhokhov 2019-04-17 15:17:27 -07:00
• b83a66527d Add jrl19 as backend for workbench (#324) John Schulman 2019-04-17 10:13:12 -07:00
• 07cbf1e26a Grad clipping in MpiAdamOptimizer, transformer changes (#304) John Schulman 2019-04-16 09:20:09 -07:00
• 5082e5d34b Workbench (#303) Karl Cobbe 2019-04-04 13:52:00 -07:00
• 376fd88bb8 fix vec monitor infos Christopher Hesse 2019-04-03 16:28:29 -07:00
• 3301089b48 remove bullet extra, constrain gym version to be >= 0.10.0 (#885) pzhokhov 2019-04-26 16:14:49 -07:00
• a07fad9066 change rms 2 tfrms switch in vec_normalize to be more explicit (#886) pzhokhov 2019-04-26 16:14:21 -07:00
• fc0c43b199 RNN support for PPO2 (#859) stateful_rnn JongGyun Kim 2019-04-27 07:17:57 +09:00
• 5d8041d18e Fix indexing LazyFrames (#875) Taeyeong Jeong 2019-04-20 07:00:09 +09:00
• fa37beb52e fix commit on atari bms page to point to a public commit Peter Zhokhov 2019-04-06 20:03:32 -07:00
• 8a97e0df10 fix shuffling bug in ppo1 Peter Zhokhov 2019-04-05 15:23:46 -07:00
• fabbf2c611 short-circuit framestack wrapper with size 1 (#871) pzhokhov 2019-04-05 15:18:15 -07:00
• 5d285b318f [Update misc_util.py]: clean up unused helper functions (#751) Xingdong Zuo 2019-04-06 00:16:26 +02:00
• 3e13bb8dc8 short-circuit framestack wrapper with size 1 like_pr_787 Peter Zhokhov 2019-04-05 15:13:59 -07:00
• 49a99c7d23 Add eps to normalization (#797) Tim Zaman 2019-04-05 14:46:01 -07:00
• c79b3373bf parse colon-separated env_id's Peter Zhokhov 2019-04-05 14:43:09 -07:00
• 96b6a31848 Merge branch 'internal' of github.com:openai/baselines into internal Peter Zhokhov 2019-04-05 14:11:09 -07:00
• 0a48a1fda9 Merge branch 'master' of github.com:openai/baselines into internal Jacob Hilton 2019-04-03 16:21:48 -07:00
• ea20c8a034 add score calculator wrapper, forward property lookups on vecenv wrap… (#300) Christopher Hesse 2019-03-27 14:36:28 -07:00
• a08af5d07d make tests use single-threaded session for determinism of KfacOptimizer (#298) pzhokhov 2019-03-22 16:28:29 -07:00
• cc88c8e4c0 remove tensorflow dependency from VecEnv Oleg Klimov 2019-03-18 10:58:23 -07:00
• f2654082b2 Symshapes - gives codegen ability to evaluate same algo on envs with different ob/ac shapes (#262) pzhokhov 2019-03-01 17:11:47 -08:00
• dadc2c2eb6 Rl19 metalearning (#261) Karl Cobbe 2019-03-01 16:41:17 -08:00
• d9702e7ccb codegen continuous control experiment pr (#256) pzhokhov 2019-02-28 20:13:05 -08:00
• f641810ef9 update dmlab30 env (#258) Christopher Hesse 2019-02-27 22:46:43 +00:00
• 3265098cc6 Merge branch 'master' of github.com:openai/baselines into internal Peter Zhokhov 2019-04-01 16:26:25 -07:00
• 6d1c6c78d3 Interface for U.make_session changed (#865) Sridhar Thiagarajan 2019-04-01 16:24:02 -07:00
• 62a9c76f18 fix the definition of TfInput.make_feed_dict. (#812) JongGyun Kim 2019-04-02 07:49:25 +09:00
• 282c9cc91f fix small bug in plot_results() (#864) Hao-Chih, Lin 2019-04-02 00:48:35 +02:00
• 096f4d9cf0 neaten up stacking logic in mujoco_dset in gail Peter Zhokhov 2019-04-01 15:47:13 -07:00
• 16136ddca7 fix bugs: obs_ph normalization in adversary.py (#823) Mingfei 2019-04-02 06:44:31 +08:00
• b1644157d6 Fixed typo on #092 (#824) Darío Hereñú 2019-04-01 19:41:52 -03:00
• 58541db226 MPI refer to workers as ranks, not threads. (#833) Yu Feng 2019-04-01 15:38:45 -07:00
• c02b575f01 ppo2: use time.perf_counter() instead of time.time() for time measurement (#847) zlsh80826 2019-04-02 06:37:32 +08:00
• 897fa31548 Avoid using default config while requesting available GPUs (#863) Pastafarianist 2019-03-29 23:25:56 +03:00
• d51f8be8f9 Report episode rewards/length in A2C and ACKTR (#856) Brett Daley 2019-03-28 12:21:48 -04:00
• 3f2f45acef Merge pull request #860 from openai/build-retro-env-framestack-fix Jacob Hilton 2019-03-25 14:33:15 -07:00
• b64974eb90 build_env now doesn't apply frame stack to retro games twice Jacob Hilton 2019-03-24 12:27:14 -07:00
• 6bbc4635e6 Update cmd_util with initializer, env_kwargs, and force_dummy gdb Greg Brockman 2019-03-18 17:42:10 -07:00
• 1b092434fc remove f-strings for python 3.5 compatibility (#854) pzhokhov 2019-03-16 11:54:47 -07:00
• 1259f6ab25 check for environment being vectorized in the play logic in run.py Peter Zhokhov 2019-03-11 17:44:03 -07:00
• 5bc6f53960 merged master Peter Zhokhov 2019-03-11 17:31:03 -07:00
• 74101a9f24 fix freeze of ppo2 (#849) pzhokhov 2019-03-11 17:28:51 -07:00
• 90d66776a4 remove one of duplicated lines. (#813) JongGyun Kim 2019-03-07 08:13:01 +09:00
• b875fb7b5e release Internal changes (#800) pzhokhov 2019-02-27 15:35:31 -08:00
• fa5cb1e1f5 merged master Peter Zhokhov 2019-02-27 15:05:24 -08:00
• 675b100190 raised the tolerance on the test_microbatches test Peter Zhokhov 2019-02-27 14:22:24 -08:00
• adc4388f6b fixes to catch changes in gym Peter Zhokhov 2019-02-27 12:49:40 -08:00
• 6dedd5d241 flake8 complaints in baselines/her Peter Zhokhov 2019-02-26 16:50:10 -08:00
• 5c7da772a4 Merge branch 'master' of github.com:openai/games Peter Zhokhov 2019-02-26 15:44:26 -08:00