Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
314 commits
Select commit Hold shift + click to select a range
d489313
feature(nyz): setup evogym docker (#580)
PaParaZz1 Feb 12, 2023
d03893a
feature(nyz): add ppof ch3 demo (#581)
PaParaZz1 Feb 13, 2023
7f2e36e
fix(nyz): fix CkptSaver and env manager interface compatibility bug (…
PaParaZz1 Feb 13, 2023
bd46c7d
style(nyz): extend treetensor lowest version(ci skip)
PaParaZz1 Feb 14, 2023
0472a3a
feature(zt): add metadrive-simulator env and related onppo config (#574)
timothijoe Feb 15, 2023
8b1f05b
fix(nyz): fix gym env deepcopy spec bug
PaParaZz1 Feb 15, 2023
f1f0b55
fix(nyz): fix ppof collect_data and deploy cuda mismatch bug
PaParaZz1 Feb 16, 2023
c11f052
v0.4.6
PaParaZz1 Feb 17, 2023
0b4180c
style(nyz): fix v0.4.6 version id bug(ci skip)
PaParaZz1 Feb 18, 2023
1e6f503
fix(nyz): fix deque buffer wrapper PER bug (#586)
PaParaZz1 Feb 20, 2023
f3b5a67
style(nyz): add d4rl docker (#591)
PaParaZz1 Feb 22, 2023
e89fb6b
fix(nyz): fix evaluator return_info tensor type bug (#592)
PaParaZz1 Feb 24, 2023
6824669
style(nyz): update introduction(ci skip)
PaParaZz1 Mar 1, 2023
20cf318
style(nyz): polish readme and add treetensor example(ci skip)
PaParaZz1 Mar 1, 2023
203be4b
style(nyz): add diff example for treetensor(ci skip)
PaParaZz1 Mar 1, 2023
737af2f
style(nyz): fix typos and polish ci deploy(ci skip)
PaParaZz1 Mar 2, 2023
8c33420
fix(psharold): unsqueeze action_args in PDQN when shape is 1 (#599)
PSHarold Mar 2, 2023
2c8d02e
fix(nyz): update ptz to latest version (#597)
PaParaZz1 Mar 2, 2023
ac08231
style(elt): fix typo in time_helper.py (#602)
eltociear Mar 5, 2023
072370a
fix(lisong): fix icm/rnd+onppo config bugs and app_key env bugs (#564)
song2181 Mar 5, 2023
3b108aa
fix(nyz): fix reward model save method compatibility bug
PaParaZz1 Mar 6, 2023
b7ce258
feature(lxy): modify ppof rewardclip and add atari config (#589)
karroyan Mar 6, 2023
67032d7
polish(nyz): polish comment and clean code about SAC
PaParaZz1 Mar 7, 2023
d72df0d
fix(nyz): fix SAC old value network notation bug
PaParaZz1 Mar 7, 2023
55898a3
style(nyz): update doc links
PaParaZz1 Mar 7, 2023
741fe40
feature(gry): add MDQN algorithm (#590)
ruoyuGao Mar 8, 2023
8e9ecaf
feature(rjy): add dmc2gym+sac baseline both in state input and pixel …
nighood Mar 8, 2023
b81ce53
polish(nyz): polish QAC with ConvEncoder
PaParaZz1 Mar 8, 2023
f798002
fix(nyz): polish dmc2gym sac entry
PaParaZz1 Mar 8, 2023
7601e03
feature(whl): add PC algorithm (#514)
kxzxvbk Mar 9, 2023
3b43ec0
fix(nyz): fix bfs test py3.9 compatibility bug
PaParaZz1 Mar 10, 2023
275141b
feature(nyz): add PPOF ch4 reward demo suuport (#608)
PaParaZz1 Mar 10, 2023
cdb5ffa
feature(zjow): add wandb logger features; fix relative bugs for wandb…
zjowowen Mar 16, 2023
f70ac63
style(nyz): fix flake8 style(ci skip)
PaParaZz1 Mar 16, 2023
503d273
polish(gry): polish dqn config (#611)
ruoyuGao Mar 20, 2023
405191d
fix(nyz): fix logger assertion and unittest bug
PaParaZz1 Mar 21, 2023
7b24712
refactor(nyz): remove policy cfg sub fields requirements (#620)
PaParaZz1 Mar 22, 2023
0c74338
style(nyz): update contributing doc(ci skip)
PaParaZz1 Mar 24, 2023
5b2507a
fix(jimmy): fix typo in task
jimmydengpeng Mar 28, 2023
ae12519
polish(nyz): polish lunarlander c51 and viz results
PaParaZz1 Mar 28, 2023
afcfa51
polish(nyz): add lunarlander continuous TD3/SAC config
PaParaZz1 Mar 28, 2023
e873d9e
fix(nyz): fix zergling collector unittest bug
PaParaZz1 Mar 29, 2023
23775e9
feature(wgt): add torch-rpc fix dockerfile (#628)
SolenoidWGT Apr 1, 2023
cd10e58
test(nyz): disable some distributer unittests
PaParaZz1 Apr 2, 2023
a580019
polish(gry): polish reward model and td error (#624)
ruoyuGao Apr 3, 2023
44226be
feature(whl): add gpt utils (#625)
kxzxvbk Apr 6, 2023
1cb1038
feature(lxy): add popart & value rescale & symlog to ppof (#605)
karroyan Apr 7, 2023
283ef35
fix(nyz): fix confusing shallow copy operation about next_obs (#641)
PaParaZz1 Apr 11, 2023
3447f57
v0.4.7
PaParaZz1 Apr 11, 2023
dd00ebf
feature(wgt): add barrier middleware (#570)
SolenoidWGT Apr 16, 2023
4c182f6
fix(nyz): fix to_item compatibility bug (#646)
PaParaZz1 Apr 18, 2023
be61e76
feature(zjow): add PPO demo for complex env observation (#644)
zjowowen Apr 19, 2023
93e4fa5
fix(nyz): fix trainer dtype transform compatibility bug
PaParaZz1 Apr 20, 2023
aefddac
feature(zc): add EDAC and modify config of td3bc (#639)
Super1ce Apr 25, 2023
9e7002f
fix(pu): fix last_linear_layer_weight_bias_init_zero in MLP and add i…
puyuan1996 Apr 25, 2023
a82caab
fix(nyz): fix ensemble head unittest bug
PaParaZz1 Apr 26, 2023
b094f5e
fix(zjow): fix incompatible gym version bug in Dockerfile.env (#653)
zjowowen Apr 27, 2023
6f73fe2
fix(eltociear): typo in gyn any_trading env (#654)
eltociear Apr 28, 2023
7f2b6de
fix(zjow): fix atari env id (#655)
zjowowen May 6, 2023
42b3fc1
fix(lxy): add normal value norm baseline (#658)
karroyan May 8, 2023
fa521b0
fix(nyz): polish bipedalwalker configs and fix default stop_value config
PaParaZz1 May 9, 2023
a8f0ac9
polish(pu): add LN and GN norm_type support in ResBlock (#660)
puyuan1996 May 11, 2023
5ae99ed
feature(nyz): add MAPPO/MASAC task example (#661)
PaParaZz1 May 12, 2023
27df79a
fix(zjow): update td3bc d4rl config (#659)
zjowowen May 13, 2023
fccb8f4
fix(zp): add record_random_collect option (#662)
zhangpaipai May 16, 2023
4023c59
fix(nyz): fix pettingzoo 1.23.0 compatibility bug
PaParaZz1 May 16, 2023
164cb1a
fix(nyz): fix gym hybrid reward dtype bug (#664)
PaParaZz1 May 22, 2023
42c9a23
fix(nyz): fix td3 policy monitor var and example
PaParaZz1 May 25, 2023
7eb342c
v0.4.8
PaParaZz1 May 25, 2023
5804402
style(nyz): fix pypi release actions ubuntu 18.04 bug (ci skip)
PaParaZz1 May 25, 2023
ebae45b
fix(nyz): fix cql example entry wrong config bug
PaParaZz1 May 29, 2023
6029beb
feature(zc): add bcq algorithm (#640)
Super1ce May 30, 2023
caf8b4c
fix(nyz): polish requirements and fix to_item unittest bug
PaParaZz1 May 31, 2023
2ab7c44
polish(nyz): simplify requirements (#672)
PaParaZz1 May 31, 2023
6b188c9
Doc(zjow): Huggingface badge (#674)
zjowowen Jun 3, 2023
faf4aab
feature(cy): add tensor stream merging tools (#673)
Cloud-Pku Jun 10, 2023
d6cd329
feature(cxy): add cliffwalking env (#677)
Mossforest Jun 21, 2023
fda6f7d
feature(nyz): fix py37 macos ci bug and update default pytorch to 1.1…
PaParaZz1 Jun 26, 2023
b188e29
feature(yzj): add scatter connection model (#680)
jayyoung0802 Jun 30, 2023
41ca06c
polish(nyz): polish offpolicy RL multi-gpu DDP training (#679)
PaParaZz1 Jul 13, 2023
49f2e20
fix(nyz): fix enable_save_figure env interface
PaParaZz1 Jul 18, 2023
c53a3da
fix(nyz): fix redundant env info bug in evaluator
PaParaZz1 Jul 21, 2023
e0c56bb
doc(nyz): polish edac and mbsac doc tables(ci skip)
PaParaZz1 Jul 31, 2023
28289f0
doc(zjow): update README.md with openxlab badge (#695)
zjowowen Aug 1, 2023
1074bab
feature(zp): add dreamerv3 algorithm (#652)
zhangpaipai Aug 7, 2023
ce5e50c
style(nyz): polish dreamerv3 code style and add readme link
PaParaZz1 Aug 7, 2023
521284b
test(nyz): fix dreamer unittest bugs
PaParaZz1 Aug 7, 2023
49fc489
fix(nyz): fix evaluator return episode_info compatibility bug
PaParaZz1 Aug 7, 2023
d905ca8
feature(zjow): add middleware for ape-x structure pipeline (#696)
zjowowen Aug 11, 2023
e3a7935
fix(zyz): fix type spell error (#704)
yizhengzhang1 Aug 15, 2023
3638eab
feature(pu): add three variants of Bilinear classes and a FiLM class …
puyuan1996 Aug 15, 2023
3c3de81
fix(nyz): fix merge unittest bug
PaParaZz1 Aug 16, 2023
aec6e9c
feature(whl): add example of dqn eval (#706)
kxzxvbk Aug 16, 2023
bc3ecd9
fix(lixuelin): to_ndarray fails to assign dtype for scalars (#708)
lxl2gf Aug 18, 2023
3a73dd4
refactor(lyd): refactor dt_policy in new pipeline and add img input …
AltmanD Aug 19, 2023
08c42fa
style(nyz): polish readme and update wechat (ci skip)
PaParaZz1 Aug 20, 2023
0192aad
fix(nyz): fix dt dataset compatibility bug
PaParaZz1 Aug 20, 2023
cacab2e
fix(nyz): add cartpole dt config
PaParaZz1 Aug 21, 2023
6e139b6
fix(nyz): fix offline mem data fetcher unittest bug
PaParaZz1 Aug 21, 2023
7451f46
fix(nyz): fix unittest bugs
PaParaZz1 Aug 21, 2023
c299fb9
fix(zjow): fix mujoco-py compatibility issue for cython<3 (#711)
zjowowen Aug 22, 2023
3fa8a01
fix(nyz): fix offline data fetcher bugs
PaParaZz1 Aug 22, 2023
e9d8194
config(nyz): add lunarlander ppo config and example
PaParaZz1 Aug 23, 2023
3059479
v0.4.9
PaParaZz1 Aug 23, 2023
0968250
feature(lxy): add dropout layers to dqn (#712)
karroyan Aug 28, 2023
b06ce44
fix(nyz): fix mlp dropout if condition bug
PaParaZz1 Aug 28, 2023
23fac67
fix(nyz): fix logger middleware problems (#715)
PaParaZz1 Aug 31, 2023
efa59b2
fix(nyz): fix drex collecting data unittest bugs
PaParaZz1 Aug 31, 2023
3659d81
feature(whl): add tabmwp env and prompt pg policy (#667)
kxzxvbk Sep 4, 2023
fb0f739
style(nyz): polish readme(ci skip)
PaParaZz1 Sep 4, 2023
6137b5e
style(nyz): polish env manager/wrapper comments
PaParaZz1 Sep 7, 2023
d24b8f9
style(nyz): polish model common modules comments
PaParaZz1 Sep 9, 2023
a07cde2
style(nyz): polish model template comments (#722)
PaParaZz1 Sep 13, 2023
a37981e
feature(zjow): add new pipeline agent sac/ddpg/a2c (#637)
zjowowen Sep 14, 2023
9299826
fix(luyd): fix new pipeline impala in Lunarlander and Atari env (#713)
AltmanD Sep 15, 2023
6e93b4c
fix(nyz): fix ppo parallel bug (#709)
PaParaZz1 Sep 15, 2023
def473f
style(eltociear): fix typo in optimizer_helper.py (#726)
eltociear Sep 17, 2023
f131c36
fix(zjow): fix typo for QAC class (#729)
zjowowen Sep 18, 2023
0401412
test(luyd): add model test code (#728)
AltmanD Sep 19, 2023
5d59c81
fix(nyz): fix model unittest style and bugs
PaParaZz1 Sep 19, 2023
6a26e98
polish(cy): polish anytrading (#731)
Cloud-Pku Sep 20, 2023
08a6c52
feature(zjow): polish ppof agent code for opendilab huggingface (#730)
zjowowen Sep 21, 2023
92ac919
doc(zjow): polish rl_utils doc (#724)
zjowowen Oct 7, 2023
b7f703e
doc(whl): add code doc for LT,DT,PC,BC models (#734)
kxzxvbk Oct 9, 2023
11cc7de
style(nyz): update readme info
PaParaZz1 Oct 9, 2023
5d5489f
feature(luyd): add collector logging in new pipeline (#735)
AltmanD Oct 16, 2023
26c9e80
polish(rjy): polish comments of qmix/pdqn/mavac (#736)
nighood Oct 16, 2023
2aa3165
env(zjow): add Huggingface model card support for ppof envs (#737)
zjowowen Oct 16, 2023
e6eea3d
fix(nyz): fix api doc bugs
PaParaZz1 Oct 16, 2023
817b215
doc(zjow): update README.md and Colab demo (#733)
zjowowen Oct 17, 2023
208ed38
doc(whl): polish doc for data_helper, model_helper, parameter, metric…
kxzxvbk Oct 18, 2023
88ce090
fix(nyz): fix unittest bugs and polish readme
PaParaZz1 Oct 18, 2023
8834c21
feature(zc): add plan diffuser (#700)
PaParaZz1 Oct 26, 2023
eee2239
style(nyz): update metaworld image (ci skip, metaworld docker)
PaParaZz1 Oct 30, 2023
3034731
polish(pu): polish comments in env_wrappers.py and ding_env_wrapper.p…
puyuan1996 Oct 31, 2023
c005205
polish(rjy): polish comments in wqmix/ngu/pg model (#739)
nighood Oct 31, 2023
111bf24
polish(nyz): polish dqn and ppo comments (#732)
PaParaZz1 Oct 31, 2023
439680a
fix(nyz): fix unittest bugs
PaParaZz1 Oct 31, 2023
c5a4be3
doc(zjow): polish ding model common/template note (#741)
zjowowen Nov 1, 2023
e9a978e
polish(nyz): polish api doc comments problems
PaParaZz1 Nov 1, 2023
043001b
polish(zc): change PD config name (#749)
Super1ce Nov 6, 2023
4f8f82a
v0.5.0
PaParaZz1 Dec 5, 2023
5788265
polish(rjy): polish comments in normalizer_helper and lock_helper (#752)
nighood Dec 11, 2023
b959eb1
feature(luyd): fix dt new pipeline of mujoco (#754)
AltmanD Dec 11, 2023
7342585
polish(rjy): polish the comments of collate_fn/profiler_helper/metric…
nighood Dec 14, 2023
1e6f351
fix(zjow): fix bug in cliffwalking env (#759)
zjowowen Dec 15, 2023
9116ba6
doc(whl): polish doc for loss, compression helper and bfs helper. (#747)
kxzxvbk Dec 20, 2023
a2b5ab7
fix(nyz): fix structured action bug (#760)
PaParaZz1 Dec 21, 2023
cfbd7ea
fix(nyz): fix unittest bugs
PaParaZz1 Dec 21, 2023
c1c5ffd
fix(nyz): fix comm unittest bug
PaParaZz1 Dec 22, 2023
779b4b8
fix(nyz): fix pynng requirements bug
PaParaZz1 Dec 27, 2023
4d53074
doc(zjow): add API doc for ding agent (#758)
zjowowen Dec 27, 2023
d555792
polish(nyz): change default max retry from 5 to 1
PaParaZz1 Dec 28, 2023
ac9fa76
feature(nyz): add ptz replay video demo
PaParaZz1 Dec 28, 2023
beb91d9
polish(pu): polish comments and styles in files within torch_utils/ne…
puyuan1996 Dec 28, 2023
d7a61c2
fix(pu): fix hppo entropy_weight to avoid nan error in log_prob (#761)
puyuan1996 Dec 29, 2023
6994a67
polish(nyz): polish dt entry
PaParaZz1 Jan 8, 2024
4738444
feature(rjy): add HAPPO algorithm (#717)
nighood Jan 11, 2024
b530c37
fix(nyz): fix env typo bugs
PaParaZz1 Jan 15, 2024
e89ba4c
doc(rjy): polish d4pg/ppg/qrdqn policy doc (#762)
nighood Jan 22, 2024
60d3b4d
polish(pu): polish NGU atari configs (#767)
puyuan1996 Jan 22, 2024
25a0d4d
doc(zjow): polish the notation of classes and functions in torch_util…
zjowowen Jan 23, 2024
a57bc30
fix(nyz): fix EDAC bugs
PaParaZz1 Jan 23, 2024
74c6a1e
polish(pu): polish comments in a2c/bcq/fqf/ibc policy (#768)
puyuan1996 Jan 25, 2024
acd23e5
polish(rjy): polish pg/iqn/edac policy doc (#764)
nighood Jan 29, 2024
09f8394
polish(nyz): polish api doc details
PaParaZz1 Jan 31, 2024
6a20ae3
fix(nyz): fix lock type bug
PaParaZz1 Jan 31, 2024
2405639
feature(cy): add dreamerV3 + MiniGrid code (#725)
Cloud-Pku Feb 1, 2024
c2cc99c
feature(zjow): add qgpo policy for new DI-engine pipeline (#757)
zjowowen Feb 4, 2024
e9c09f6
fix(nyz): fix dreamer unittest bug
PaParaZz1 Feb 4, 2024
abdf68a
feature(nyz): add MADDPG pettingzoo example (#774)
PaParaZz1 Feb 4, 2024
fb24992
v0.5.1
PaParaZz1 Feb 4, 2024
e28438c
fix(eltociear): typo in config.py (#776)
eltociear Feb 20, 2024
0591b5e
feature(ooo): add deprecated function decorator (#778)
ooooo-create Mar 7, 2024
c999b07
demo(nyz): add naive PWIL demo
PaParaZz1 Mar 11, 2024
aeb4c9c
feature(xrk): add new env named Flozen Lake and DQN algorithm. (#781)
rongkunxue Mar 13, 2024
6c36145
style(nyz): add discord link (ci skip)
PaParaZz1 Apr 2, 2024
7d05491
fix(zjow): fix complex obs demo for ppo pipeline (#786)
zjowowen Apr 7, 2024
1ed8afc
feature(nyz): add GPU utils (#788)
PaParaZz1 Apr 8, 2024
c469f2e
style(hus): update discord invitation (ci skip)
TuTuHuss Apr 12, 2024
caacd6f
style(hus): update discord invitation(ci skip)
TuTuHuss Apr 12, 2024
15ff277
style(hus): update discord invitation badge (ci skip)
TuTuHuss Apr 12, 2024
96c4955
polish(nyz): polish rl_utils api docs
PaParaZz1 Apr 15, 2024
1ac9ad5
config(nyz): fix masac smac config multi_agent=True bug (#791)
PaParaZz1 Apr 16, 2024
8392206
env(rjy): add ising model env (#782)
nighood Apr 23, 2024
c7c3bac
fix(nyz): fix marl nstep td compatibility bug
PaParaZz1 Apr 24, 2024
fd2d6ff
doc(hus): update discord link and badge in readme (#795)
TuTuHuss May 6, 2024
66ff69b
style(nyz): disable platform test in py3.7
PaParaZz1 May 6, 2024
fea4b9e
fix(nyz): fix unittest and platformtest bug
PaParaZz1 May 7, 2024
ecedc08
polish(nyz): polish ci python version
PaParaZz1 May 8, 2024
a45d051
polish(nyz): polish macos platform test version to 12
PaParaZz1 May 8, 2024
b2aab8d
config(nyz): update/speed up pendulum ppo
PaParaZz1 May 24, 2024
13a6d45
fix(nyz): fix gtrxl compatibility bug (#796)
PaParaZz1 May 28, 2024
d919fa5
feature(wrh): add taxi env (#799)
ruiheng123 May 30, 2024
f5fed7c
polish(zym): optimize ppo continuous act (#801)
YinminZhang Jun 13, 2024
8f3f9eb
style(hus): add new badge (hellogithub) in readme (#805)
TuTuHuss Jun 17, 2024
91bc342
fix(nyz): add constraint about numpy<2
PaParaZz1 Jun 20, 2024
73ff16f
feature(wrh): add taxi env latest version and dqn config (#807)
ruiheng123 Jun 20, 2024
97aa35d
fix(nyz): fix pyecharts import bug
PaParaZz1 Jun 22, 2024
22fe9b7
fix(nyz): fix itsdangerous==2.0.1 import bug
PaParaZz1 Jun 22, 2024
ec98a33
style(nyz): relax flask requirement (#811)
PaParaZz1 Jun 26, 2024
b4ab08a
v0.5.2
PaParaZz1 Jun 27, 2024
35ec39e
fix(nyz): fix mappo adv compute bug (#812)
PaParaZz1 Jul 1, 2024
7f95159
feature(zym): update ppo config to support discrete action space (#809)
YinminZhang Jul 1, 2024
96ccaed
feature(nyz): adapt DingEnvWrapper to gymnasium (#817)
PaParaZz1 Jul 6, 2024
d88ebe2
polish(nyz): polish api doc details
PaParaZz1 Jul 6, 2024
2037035
polish(nyz): remove unused config fields in mujoco PPO
PaParaZz1 Jul 19, 2024
a54d475
style(nyz): polish citation authors(ci skip)
PaParaZz1 Jul 29, 2024
ae3ddc6
feature(nyz): add encoder in MAVAC (#823)
PaParaZz1 Aug 14, 2024
44d5479
polish(TairanMK): update trading env (#831)
TairanMK Sep 18, 2024
6ae1396
polish(mark): add hybrid action space support to ActionNoiseWrapper (…
MarkHolmstrom Sep 20, 2024
3898386
feature(whl): add AWR algorithm (#828)
kxzxvbk Sep 26, 2024
1f198e9
feature(pu): add resume_training option to allow the envstep and trai…
puyuan1996 Nov 5, 2024
1158cd5
feature(pu): add pistonball_env, its unittest and qmix config (#833)
puyuan1996 Nov 25, 2024
de9ada0
fix(nyz): downgrade pyecharts log level to warning and polish install…
PaParaZz1 Nov 27, 2024
548406f
fix(nyz): fix priority buffer delete bug (#844)
PaParaZz1 Dec 2, 2024
e93b5a6
fix(nyz): fix middleware collector env reset bug (#845)
PaParaZz1 Dec 3, 2024
5615816
fix(nyz): fix multiple model wrappers reset bug (#846)
PaParaZz1 Dec 5, 2024
1f4ca6b
fix(nyz): upgrade macos version from 12 to 13
PaParaZz1 Dec 7, 2024
c0c65f1
fix(nyz): remove box2d in platformtest
PaParaZz1 Dec 7, 2024
bbc9cc4
feature(xyy): add HPT model to implement PolicyStem+DuelingHead (#841)
luodi-7 Dec 8, 2024
571229e
fix(nyz): fix test requirements pygame problem
PaParaZz1 Dec 8, 2024
765b8fb
fix(nyz): fix many unittest bugs
PaParaZz1 Dec 9, 2024
aa86aa7
fix(nyz): fix mock and config bugs
PaParaZz1 Dec 12, 2024
317e775
fix(nyz): fix wandb requirements bug
PaParaZz1 Dec 13, 2024
580ea65
fix(nyz): fix rmsprop bug in torch 1.13.1
PaParaZz1 Dec 13, 2024
9a6e46f
feature(pu): add ddp config of dqn and onppo (#842)
puyuan1996 Dec 19, 2024
f60b377
v0.5.3
PaParaZz1 Dec 23, 2024
f5157c7
fix(nyz): fix env check bugs (#852)
PaParaZz1 Jan 13, 2025
4e92de5
fix(nyz): fix env check multi-discrete bug (#852)
PaParaZz1 Jan 23, 2025
bf258f8
test(nyz): upgrade python version and setup-python version
PaParaZz1 Jan 24, 2025
dae7673
feature(zjow): add Implicit Q-Learning (#821)
zjowowen Jan 27, 2025
3292384
style(nyz): fix flake8 code style (ci skip)
PaParaZz1 Jan 27, 2025
64efcb3
polish(pu): delete unused enable_fast_timestep argument (#855)
puyuan1996 Jan 27, 2025
abcf972
feature(nyz): add rlhf dataset (#854)
PaParaZz1 Feb 6, 2025
8f48cb1
feature(nyz&dcy): add LLM/VLM RLHF loss (PPO/GRPO/RLOO) (#857)
PaParaZz1 Mar 1, 2025
6c2ca2f
style(nyz): polish rl_utils style details (ci skip)
PaParaZz1 Mar 1, 2025
b771e96
style(nyz): update atari link (ci skip)
PaParaZz1 Mar 10, 2025
2ab7747
feature(pu): adapt to unizero-multitask ddp, and adapt ppo to support…
puyuan1996 Mar 13, 2025
605b457
fix(nyz): fix docker deploy cache actions bug
PaParaZz1 Mar 13, 2025
101d586
style(nyz): add rust installation in docker
PaParaZz1 Mar 15, 2025
c290a67
demo(nyz): add ppo lunarlander continuous example
PaParaZz1 Mar 17, 2025
cf72cc0
fix(pu): fix noise layer's usage based on the original paper (#866)
puyuan1996 Jun 3, 2025
f6ee768
style(nyz): fix flake8 style(ci skip)
PaParaZz1 Jun 6, 2025
486bb30
feature(wyx): add three KL-divergence variants (#870)
xiaoyi1734 Jul 29, 2025
f78aed1
doc(nyz): create SECURITY.md
PaParaZz1 Oct 22, 2025
8d29a32
fix(nyz): fix multi-machine gpu id bug (#875)
PaParaZz1 Dec 6, 2025
1854e58
fix(nyz): fix ppo logit pretrained compatibility bugs
PaParaZz1 Dec 6, 2025
aa780e6
fix(nyz): fix unittest compatibility bugs
PaParaZz1 Dec 6, 2025
d0b21d0
doc(nyz): disable doc docker
PaParaZz1 Dec 7, 2025
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
The table of contents is too big for display.
Diff view
Diff view
  •  
  •  
  •  
2 changes: 2 additions & 0 deletions .coveragerc
Original file line number Diff line number Diff line change
@@ -1,10 +1,12 @@
[run]
concurrency = multiprocessing,thread
omit =
ding/utils/slurm_helper.py
ding/utils/file_helper.py
ding/utils/linklink_dist_helper.py
ding/utils/pytorch_ddp_dist_helper.py
ding/utils/k8s_helper.py
ding/utils/tests/test_k8s_launcher.py
ding/utils/time_helper_cuda.py
ding/utils/time_helper_base.py
ding/utils/data/tests/test_dataloader.py
Expand Down
7 changes: 4 additions & 3 deletions .github/workflows/algo_test.yml
Original file line number Diff line number Diff line change
Expand Up @@ -16,12 +16,12 @@ jobs:
if: "!contains(github.event.head_commit.message, 'ci skip')"
strategy:
matrix:
python-version: [3.7, 3.8, 3.9]
python-version: [3.8, 3.9]

steps:
- uses: actions/checkout@v2
- uses: actions/checkout@v4
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v2
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: do_algotest
Expand All @@ -31,5 +31,6 @@ jobs:
run: |
python -m pip install .
python -m pip install ".[test,k8s]"
python -m pip install transformers
./ding/scripts/install-k8s-tools.sh
make algotest
4 changes: 2 additions & 2 deletions .github/workflows/badge.yml
Original file line number Diff line number Diff line change
Expand Up @@ -12,13 +12,13 @@ jobs:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: [ 3.7 ]
python-version: [ 3.8 ]
env:
GIST_ID: 3690cccd811e4c5f771075c2f785c7bb
steps:
- uses: actions/checkout@v2
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v2
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: Download cloc
Expand Down
91 changes: 79 additions & 12 deletions .github/workflows/deploy.yml
Original file line number Diff line number Diff line change
Expand Up @@ -3,11 +3,10 @@ name: deploy # deploy docker
on:
push:
branches: [main, '*deploy*', '*docker*']

jobs:
docker_base:
runs-on: ubuntu-latest
# if: "contains(github.event.head_commit.message, 'enable docker')"
if: "!contains(github.event.head_commit.message, 'ci skip')"
strategy:
matrix:
platform: [linux/amd64]
Expand Down Expand Up @@ -48,7 +47,7 @@ jobs:
uses: docker/setup-buildx-action@v1

- name: Cache Docker layers
uses: actions/cache@v2
uses: actions/cache@v4
with:
path: /tmp/.buildx-cache
key: ${{ runner.os }}-buildx-${{ github.sha }}
Expand Down Expand Up @@ -80,11 +79,10 @@ jobs:

docker_doc:
runs-on: ubuntu-latest
# if: "contains(github.event.head_commit.message, 'enable docker')"
if: "contains(github.event.head_commit.message, 'doc docker')"
strategy:
matrix:
platform: [linux/amd64]
# python-version: [3.6, 3.7, 3.8]
steps:
- name: Checkout
uses: actions/checkout@v2
Expand Down Expand Up @@ -113,7 +111,7 @@ jobs:
uses: docker/setup-buildx-action@v1

- name: Cache Docker layers
uses: actions/cache@v2
uses: actions/cache@v4
with:
path: /tmp/.buildx-cache
key: ${{ runner.os }}-buildx-${{ github.sha }}
Expand Down Expand Up @@ -144,7 +142,7 @@ jobs:
docker_atari:
runs-on: ubuntu-latest
needs: docker_base
# if: "contains(github.event.head_commit.message, 'enable docker')"
if: "!contains(github.event.head_commit.message, 'ci skip')"
strategy:
matrix:
platform: [linux/amd64]
Expand Down Expand Up @@ -172,7 +170,7 @@ jobs:
uses: docker/setup-buildx-action@v1

- name: Cache Docker layers
uses: actions/cache@v2
uses: actions/cache@v4
with:
path: /tmp/.buildx-cache
key: ${{ runner.os }}-buildx-${{ github.sha }}
Expand Down Expand Up @@ -203,7 +201,7 @@ jobs:
docker_mujoco:
runs-on: ubuntu-latest
needs: docker_base
# if: "contains(github.event.head_commit.message, 'enable docker')"
if: "!contains(github.event.head_commit.message, 'ci skip')"
strategy:
matrix:
platform: [linux/amd64]
Expand Down Expand Up @@ -231,7 +229,7 @@ jobs:
uses: docker/setup-buildx-action@v1

- name: Cache Docker layers
uses: actions/cache@v2
uses: actions/cache@v4
with:
path: /tmp/.buildx-cache
key: ${{ runner.os }}-buildx-${{ github.sha }}
Expand Down Expand Up @@ -261,7 +259,7 @@ jobs:
docker_metaworld:
runs-on: ubuntu-latest
needs: docker_base
# if: "contains(github.event.head_commit.message, 'enable docker')"
if: "contains(github.event.head_commit.message, 'metaworld docker')"
strategy:
matrix:
platform: [linux/amd64]
Expand All @@ -288,7 +286,7 @@ jobs:
uses: docker/setup-buildx-action@v1

- name: Cache Docker layers
uses: actions/cache@v2
uses: actions/cache@v4
with:
path: /tmp/.buildx-cache
key: ${{ runner.os }}-buildx-${{ github.sha }}
Expand Down Expand Up @@ -386,3 +384,72 @@ jobs:
run: |
docker buildx build -f ./docker/Dockerfile.env . -t opendilab/ding:nightly-dmc2gym --target=dmc2gym
docker push opendilab/ding:nightly-dmc2gym

docker_rpc:
runs-on: ubuntu-latest
needs: docker_base
if: "contains(github.event.head_commit.message, 'test rpc')"
strategy:
matrix:
platform: [linux/amd64]
# python-version: [3.6, 3.7, 3.8]
steps:
- name: Checkout
uses: actions/checkout@v2
- name: Login to DockerHub
uses: docker/login-action@v1
with:
username: ${{ secrets.DOCKERIO_USERNAME }}
password: ${{ secrets.DOCKERIO_PASSWORD }}

- name: Build and push
id: docker_build
run: |
docker buildx build -f ./docker/Dockerfile.rpc . -t opendilab/ding:nightly-rpc-base --target=base
docker push opendilab/ding:nightly-rpc-base

docker_evogym:
runs-on: ubuntu-latest
needs: docker_base
if: "contains(github.event.head_commit.message, 'evogym docker')"
strategy:
matrix:
platform: [linux/amd64]
# python-version: [3.6, 3.7, 3.8]
steps:
- name: Checkout
uses: actions/checkout@v2
- name: Login to DockerHub
uses: docker/login-action@v1
with:
username: ${{ secrets.DOCKERIO_USERNAME }}
password: ${{ secrets.DOCKERIO_PASSWORD }}

- name: Build and push
id: docker_build
run: |
docker buildx build -f ./docker/Dockerfile.env . -t opendilab/ding:nightly-evogym --target=evogym
docker push opendilab/ding:nightly-evogym

docker_d4rl:
runs-on: ubuntu-latest
needs: docker_mujoco
if: "contains(github.event.head_commit.message, 'd4rl docker')"
strategy:
matrix:
platform: [linux/amd64]
# python-version: [3.6, 3.7, 3.8]
steps:
- name: Checkout
uses: actions/checkout@v2
- name: Login to DockerHub
uses: docker/login-action@v1
with:
username: ${{ secrets.DOCKERIO_USERNAME }}
password: ${{ secrets.DOCKERIO_PASSWORD }}

- name: Build and push
id: docker_build
run: |
docker buildx build -f ./docker/Dockerfile.env . -t opendilab/ding:nightly-d4rl --target=d4rl
docker push opendilab/ding:nightly-d4rl
2 changes: 1 addition & 1 deletion .github/workflows/doc.yml
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@ jobs:
steps:
- uses: actions/checkout@v2
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v2
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: Generate
Expand Down
7 changes: 4 additions & 3 deletions .github/workflows/envpool_test.yml
Original file line number Diff line number Diff line change
Expand Up @@ -11,18 +11,19 @@ jobs:
if: "!contains(github.event.head_commit.message, 'ci skip')"
strategy:
matrix:
python-version: [3.7, 3.8] # Envpool only supports python>=3.7
python-version: [3.8] # Envpool only supports python>=3.7

steps:
- uses: actions/checkout@v2
- uses: actions/checkout@v4
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v2
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: do_envpool_test
run: |
python -m pip install .
python -m pip install ".[test,k8s]"
python -m pip install ".[envpool]"
python -m pip install transformers
./ding/scripts/install-k8s-tools.sh
make envpooltest
9 changes: 5 additions & 4 deletions .github/workflows/platform_test.yml
Original file line number Diff line number Diff line change
Expand Up @@ -11,19 +11,20 @@ jobs:
if: "!contains(github.event.head_commit.message, 'ci skip')"
strategy:
matrix:
os: [macos-latest, windows-latest]
python-version: [3.7, 3.8, 3.9]
os: [macos-13, windows-latest]
python-version: [3.8, 3.9]

steps:
- uses: actions/checkout@v2
- uses: actions/checkout@v4
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v2
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: do_platform_test
timeout-minutes: 30
run: |
python -m pip install .
python -m pip install ".[test,k8s]"
python -m pip install transformers
python -m pip uninstall pytest-timeouts -y
make platformtest
8 changes: 4 additions & 4 deletions .github/workflows/release.yml
Original file line number Diff line number Diff line change
Expand Up @@ -10,14 +10,14 @@ jobs:
strategy:
matrix:
os:
- 'ubuntu-18.04'
python-version: [3.7]
- ubuntu-latest
python-version: [3.8]

steps:
- name: Checkout code
uses: actions/checkout@v2
uses: actions/checkout@v4
- name: Set up python ${{ matrix.python-version }}
uses: actions/setup-python@v2
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: Set up python dependences
Expand Down
2 changes: 1 addition & 1 deletion .github/workflows/release_conda.yml
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@ jobs:
runs-on: ubuntu-latest
if: github.event_name == 'push' && (startsWith(github.ref, 'refs/tags') || contains(github.event.head_commit.message, 'conda'))
steps:
- uses: actions/checkout@v2
- uses: actions/checkout@v4
- name: publish-to-conda
uses: fcakyon/conda-publish-action@v1.3
with:
Expand Down
5 changes: 3 additions & 2 deletions .github/workflows/style.yml
Original file line number Diff line number Diff line change
Expand Up @@ -10,16 +10,17 @@ jobs:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: [3.7, 3.8, 3.9]
python-version: ['3.8', '3.9', '3.10']

steps:
- uses: actions/checkout@v2
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v2
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: code style
run: |
python -m pip install "yapf==0.29.0"
python -m pip install "flake8<=3.9.2"
python -m pip install "importlib-metadata<5.0.0"
make format_test flake_check
16 changes: 9 additions & 7 deletions .github/workflows/unit_test.yml
Original file line number Diff line number Diff line change
Expand Up @@ -8,15 +8,15 @@ on: [push, pull_request]
jobs:
test_unittest:
runs-on: ubuntu-latest
if: "!contains(github.event.head_commit.message, 'ci skip')"
if: ( !contains(github.event.head_commit.message, 'ci skip') && !contains(github.event.head_commit.message, 'ut skip'))
strategy:
matrix:
python-version: [3.7, 3.8, 3.9]
python-version: ['3.8', '3.9', '3.10']

steps:
- uses: actions/checkout@v2
- uses: actions/checkout@v4
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v2
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: do_unittest
Expand All @@ -25,6 +25,7 @@ jobs:
python -m pip install box2d-py
python -m pip install .
python -m pip install ".[test,k8s]"
python -m pip install transformers
./ding/scripts/install-k8s-tools.sh
make unittest
- name: Upload coverage to Codecov
Expand All @@ -41,17 +42,18 @@ jobs:
if: "!contains(github.event.head_commit.message, 'ci skip')"
strategy:
matrix:
python-version: [3.7, 3.8, 3.9]
python-version: ['3.8', '3.9', '3.10']

steps:
- uses: actions/checkout@v2
- uses: actions/checkout@v4
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v2
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: do_benchmark
run: |
python -m pip install .
python -m pip install ".[test,k8s]"
python -m pip install transformers
./ding/scripts/install-k8s-tools.sh
make benchmark
Loading