github.com/JuliaReinforcementLearning/ReinforcementLearning.jl commits

add GPU support for GaussianNetwork, fix #455 (#486)

Co-authored-by: Jun Tian <[email protected]>

be0c479aabbbb2064901fd39f348027ba66f9fa7 authored over 3 years ago

Update experiments of maddpg (#487)

* add continuous choice in the env

* update the env and maddpg

* update relative experimen...

6b37f54f06001a0a6f749bb705f00ac8879f5215 authored over 3 years ago

Add the experiment of `MADDPG`. (#481)

* add SpeakerListenerEnv

* update the env

* update the algorithms and ...

cce2dbcbc9cfe2c567087f89ece26a48ae536e61 authored over 3 years ago

Gym d4rl extension (#405)

* Gym env extension

Accommodates d4rl envs with the exception of flow and carla

* comment
...

521de3140d9940beace16cb88ed320059d66a0d6 authored over 3 years ago

Update manifest (#484)

9328c64869304da0331d983d81b55ceeb3914010 authored over 3 years ago

update report and add reward bonus (#483)

37a012ee2e71df512d1d4b4506443f6bf926b9a8 authored over 3 years ago

Add bsuite datasets (#482)

* Add bsuite datasets

* Fix spell check

4326df59296a6edc488b77f29c4968853280db85 authored over 3 years ago

FisherBRC algorithm and update docs (#480)

* FisherBRC algorithm and update docs

* update

596cf101803afe1e3539430a8f8975e89069e982 authored over 3 years ago

Chancestyle doc update (#479)

* mention custom dispatch of ChanceStyle

* correct the default value in doc

* Update How_t...

b137139df9518d796dd30ee30f025c5b31d6adb2 authored over 3 years ago

Update How_to_write_a_customized_environment.md

3ccf6edafc9dde4b898555a10198dab3ba517988 authored over 3 years ago

Report (#474)

* Update report

aa81a6138a6ca2b9aa915c607c1cba030aa6d3e8 authored over 3 years ago

control whether `run` displays description of experiment (#477)

55f03584f3811a41416b832092e1e1e9b4901814 authored over 3 years ago

docs: add ShuhuaGao as a contributor for code, question (#478)

* docs: update README.md [skip ci]

* docs: update .all-contributorsrc [skip ci]

Co-authore...

8e578e5e099118146698db1005f72452e2aa2704 authored over 3 years ago

Update maddpg and the report (#470)

* update trajectory_extension

* update maddpg

* update the experiment

* update the repo...

196f02a395676bbfb9d2616758e7999e777d4f0e authored over 3 years ago

update the plan of week 7 (#468)

Co-authored-by: Jun Tian <[email protected]>

6766c8f5dd7483c02362443fb3059d0f13d0acca authored over 3 years ago

Fix ci (#469)

* Fix ci

* add KellyCoinflip-v0

* Remove toy_text envs

31d133e06abb4d4e1820e79dc295b6319051725e authored over 3 years ago

Fix RLDatasets.jl documentation (#467)

* Refine documentation in RLDatasets.jl

* update docs in missed out files

* fix link provi...

b29c9f01240d6aae9e6f7acc28a0a1e95cf29f76 authored over 3 years ago

Summer ospp project 210370190 mid-term report (#449)

* update nfspagent's behavior of PreEpisodeStage

* upload the draft mid-term blog

* update...

9208cb027e68a7ca552bf5f89deb4a2a8123d679 authored over 3 years ago

Update report (#457)

* Update report

* Delete bibliography.bib.sav

* Update cspell

* update report

Co-aut...

64c87bc2a534aa37ecb0eb234227b677c67148b3 authored over 3 years ago

Update report (#453)

* Update report

* fix cspell

* Make some changes

* Update with implementation details
...

c903a3b27f6409c2cd5013ed5335878762f818ca authored over 3 years ago

fix CI (#466)

* fix CI

* udpate cspell.json

8d6c5ca0d0647e622912187dd126eabde68b3137 authored over 3 years ago

Merge pull request #465 from JuliaReinforcementLearning/Remove-license

Delete LICENSE

f65fc8ff13c63c492ce478140962452bb72de344 authored over 3 years ago

Merge branch 'master' into Remove-license

ec2239c20ff29cc08462bfc7af8f27c0000a8717 authored over 3 years ago

Delete LICENSE

ed0574fdd7f01d3c8088a7def98b8c59418ec825 authored over 3 years ago

Merge pull request #458 from Mobius1D/fix_installation_docs

fix installation docs

24ff0b3bab90c54b599ec44c647030b641725411 authored over 3 years ago

Merge branch 'master' into fix_installation_docs

8a378241b004c4eb7aa75c427be4ac2b3874cc2c authored over 3 years ago

Merge pull request #463 from Mobius1D/fix_make.jl

Fix make.jl

bf842e23d5a09669ef0bce23e94d5080fa656b35 authored over 3 years ago

Fix make.jl

8bfc5fd51a61e80cf10146fead05b57907c8ce94 authored over 3 years ago

Merge pull request #462 from Mobius1D/datasets_docs

Add docs

513246fdfbbcaa3833bbe1154a93ee4e4d3dc624 authored over 3 years ago

Merge branch 'master' into fix_installation_docs

6f33eaa27b02fc93571eabb0dba7e6c51cc2d12d authored over 3 years ago

Merge branch 'master' into datasets_docs

ad62fa8ced7affa8758f2c9da75bc522c21f9d0e authored over 3 years ago

Merge pull request #461 from JuliaReinforcementLearning/add-license-1

Create LICENSE

e198e562dac588fd9f1a861b256306b28e38b7f4 authored over 3 years ago

Merge remote-tracking branch 'Mobius1D/datasets_docs' into datasets_docs

3d668d149c2335097ba8d5bb0882dfd2d2ba32f0 authored over 3 years ago

fix cspell

211fbaa5774a367c3958058ce0eba314b43d403c authored over 3 years ago

Merge branch 'master' into datasets_docs

db23510952a3666b2834f85140d5d589725bf70f authored over 3 years ago

Add docs

2e1ffc1717b170beef364bf906adcddd3b24de26 authored over 3 years ago

Create LICENSE

a466f5f5163e7b119a093dc4f403ed9e8a2db18a authored over 3 years ago

Merge branch 'master' into fix_installation_docs

a02d21cbe509cb9d5fc24471f5a5e04ce3f30555 authored over 3 years ago

docs: add peterchen96 as a contributor for code, doc (#459)

* docs: update README.md [skip ci]

* docs: update .all-contributorsrc [skip ci]

Co-authore...

76cbac4c54c048e200c4ea6f4526885e70f42a19 authored over 3 years ago

fix installation docs

10db85dcad9d2bee0a1b70460b490d8bd0feb4c4 authored over 3 years ago

RL unplugged implementation with tests (#452)

* RL unplugged implementation with tests

* Fix NEWS.md

* Fix cspell

* Update README.md
...

66a9c7e41416c4b959c66b07d06d67915dc4b628 authored over 3 years ago

Revert "Update report (#448)" (#456)

This reverts commit e05ed4eed26bb35007a278737618a4a9e048269e.

50756bbe9e1925a9320d1abdbbc6255c1b4a27f1 authored over 3 years ago

Update report (#448)

* update report

C...

e05ed4eed26bb35007a278737618a4a9e048269e authored over 3 years ago

disable notebook generation (#454)

9731436b0f138a909ad6471f9a844a19562d04b9 authored over 3 years ago

Add pre-train step; VAE component; CRR and PLAS algorithms (#443)

* update

Co-authored-by: Jun Tian <[email protected]>

cc04e9a3a2d68dba69932dd6e8ce0eac5a9a66c9 authored over 3 years ago

docs: add burmecia as a contributor for code (#451)

* docs: update README.md [skip ci]

* docs: update .all-contributorsrc [skip ci]

Co-authore...

3d6012f7ae6699daf1654fc8bca01ec152b49bea authored over 3 years ago

add maxdepth kwarg to remove print_tree() deprecation warning (#450)

b0b8e8236524a7af0a2da8987ae2261c257f94b2 authored over 3 years ago

add MADDPG algorithm (#444)

* add maddpg

* add experiment

* update cspell.json

* update the algo

4e5d258798088b1c628401b6b9de18aa8cbb3ab3 authored over 3 years ago

try to fix bugs of ActionTransformedEnv (#447)

e460aa2c3c438b17a9b790d0d027323fa8b38bb5 authored over 3 years ago

add_Graph_Shortest_Path (#445)

* add_Graph_Shortest_Path

* update news

70785358a323e8fef4871062549c0606a4258255 authored over 3 years ago

docs: add LaarsOman as a contributor for doc (#442)

* docs: update README.md [skip ci]

* docs: update .all-contributorsrc [skip ci]

Co-authore...

497376243052afe715babc1a5845a1eef412b6f4 authored over 3 years ago

Tiny text typo (#441)

line 39
desgin -> design

111cb04463d7dbec08e9ca701bbacec0257a15ea authored over 3 years ago

update the experiment's parameters (#440)

b04e3f192e71418dbca496331ada44f65b2822d9 authored over 3 years ago

correct nfsp (#439)

cad468eb421bdc7c969a0b390cda573bbdd0d650 authored over 3 years ago

docs: add albheim as a contributor for maintenance (#438)

* docs: update README.md [skip ci]

* docs: update .all-contributorsrc [skip ci]

* docs: up...

4a963e4da5f18e463ea205b8efcb23dbb9153d76 authored over 3 years ago

Add Atari datasets released by Google Research (#429)

* WIP: atari datasets

Atari datasets released by google research.

* typo

* Tests pass
...

ade5442ea5a4ce2cabd05f310810e719c0473424 authored over 3 years ago

Modify parameter (#437)

cadb5ff6c948b691c82e34885d1f0f5b378fc3ef authored over 3 years ago

add stock trading env (#428)

* add stock trading env

* test DDPG & PPO

* update words

* update version

6060771fe03379fa48262861641286dfdefd5c26 authored over 3 years ago

add kwargs to plot(env::) (#430)

d5a397a064e11ca63d1004a564e5d9833e2ec353 authored over 3 years ago

Implementation of NFSP and NFSP_KuhnPoker experiment (#402)

* add NFSPAgent definition and example setting

* add relative functions for NFSPAgent

* ad...

0a8b796263c819fed7a7e4de294581ca1b3dc365 authored over 3 years ago

add wrapped_env[!] to access env inside wrappers (#426)

eca04df2984d805ef700d522fa4d0b2eb5bc694c authored over 3 years ago

make sac policy use internal rng (#423)

ffada88441274daed3a5ab8a387b58fe4a83004c authored over 3 years ago

Fix 418 (#420)

* fix some dead links

* add docstring for different trajectories

a77e18313a8f094e40bc863ba80126626275ea42 authored over 3 years ago

docs: add Krastanov as a contributor for doc (#422)

* docs: update README.md [skip ci]

* docs: update .all-contributorsrc [skip ci]

Co-authore...

b6f93d75580972c7d4cf882e9274f383f4d62a99 authored over 3 years ago

Fix a bug (#415)

Co-authored-by: Jun Tian <[email protected]>

2b9196066f3c5aa3f76f5d7912ced01dd4303eaa authored over 3 years ago

Expand to d4rl-pybullet (#416)

* Expand to d4rl-pybullet

Support d4rl-pybullet and make a few other changes.

* Update NEW...

6e60a1994b2d964fed174bd747dc9b9e91662e24 authored over 3 years ago

docs: add pilgrimygy as a contributor for bug (#417)

* docs: update README.md [skip ci]

* docs: update .all-contributorsrc [skip ci]

* docs: up...

625304f4300890e9b6fba3755bb928594d15e89b authored over 3 years ago

Reduce allocations and update docstring for GaussianNetwork (#414)

* reduce allocations with more dots

* bugfix

359c79b007a50747dafcb0506f8a291c28551227 authored over 3 years ago

Updated RLDatasets.jl (#403)

* Updated RLDatasets.jl

This drops most of the dependencies and updated just to use d4rl datase...

472bf301171da54de8802b47d8a7c811b2f6c6a6 authored over 3 years ago

updates as per GridWorlds v0.5.0 (#406)

* rename EmptyRoom to SingleRoomUndirected for GridWorlds.jl env

* remove loading GridWorlds ...

59545ee3bacf50b71c08003053928333ffc0bf5e authored over 3 years ago

Update index.html

63580d3e09975e90fbeabe971e3b93c44ffb2e4d authored over 3 years ago

docs: add pkienscherf as a contributor for bug (#396)

* docs: update README.md [skip ci]

* docs: update .all-contributorsrc [skip ci]

Co-authore...

d2c7a64486456d5f1f9e3255ce4bbe2c1ded23e5 authored over 3 years ago

Throw error in MultiAgentManager if it is applied to a SIMULTANEOUS env (#395)

* throw error in MultiAgentManager if it is applied to a SIMULTANEOUS env

* rephrase words

53292c3edbc554408312a1384dd0661aeea5070f authored over 3 years ago

Update NEWS.md

f915ed5151676d45c43d2b720166c2e232b84429 authored over 3 years ago

AddSequentialEnv (#394)

* add SequentialEnv wrapper

* add more meaningful tests

a46cfff9483a1ccb2b9166f1ce4e600c69563f93 authored over 3 years ago

Supplement functions in ReservoirTrajectory and BehaviorCloningPolicy (#390)

* add update! method for ReservoirTrajectory when :PreActStage

* redefine BehaviorCloningPoli...

97f603f060f09ed4de52b86addf6e5d31d815bfe authored over 3 years ago

Update Flux version (#391)

* fix CI

* fix docs generation

* fix docs genera...

2e44f95cb3a101ab180846893023fa51bba9d613 authored over 3 years ago

add weighted_softmax_explorer in the `explorers.jl` (#382)

* add weighted_softmax_explorer in the explorers

* add prob method for weighted_softmax_explorer

fc2afa7b9f78c97fc688dbe3aaed9d4d5de366f3 authored over 3 years ago

Make general components (#370)

* Make general components

* Update

* pass CI temporarily

* resolve comments

* remove...

32aa3940deed84d42ec4b9bcfd73ffcb5ccf05fd authored over 3 years ago

Add the tuning entropy component (#365)

* Add the tuning entropy component

* Bump version

* Revert "Bump version"

This reverts ...

dd17ad674f6d8b9935d2a7118d5f4ef1a83751c3 authored over 3 years ago

docs: add 00krishna as a contributor for bug (#356)

* docs: update README.md [skip ci]

* docs: update .all-contributorsrc [skip ci]

* Update R...

c7b66e47e939592045326485b9c89b1486df165d authored over 3 years ago

bump version of RLZoo (#355)

5aea1c1102d3e9f680e924295e2da9773928d4ad authored over 3 years ago

add LICENSE in RLBase (#353)

f557205a82f2a6bdac78af8b17e4ff61c1e8f64d authored over 3 years ago

bump version of RLBae (#352)

8ca2522720e2da619105bac58e3d06d20868e46d authored over 3 years ago

add Base.:(==) and Base.hash for AbstractEnv and test nash_conv on KuhnPokerEnv (#348)

* add Base.:(==) and Base.hash for AbstractEnv

* add nash_conv test for KuhnPokerEnv with Tabul...

0b6fc516a75dab68562865428c08f5080c8e55dc authored over 3 years ago

bump version of RLCore (#351)

a98ecfdd29a717653fc0c979b73a431f55e2e089 authored over 3 years ago

fix legal_actions_mask indexing error in CircularSLART (#350)

fe7f4318323aa1b4ddde3315e7532cb1e9a6313c authored over 3 years ago

Add copyto function (#345)

0aa2076423ed6a42db6dd6309ff95bc69d8df5c3 authored over 3 years ago

CompatHelper: bump compat for "FillArrays" to "0.12" for package ReinforcementLearningCore (#340)

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

995de2d56f2b88424a7bd1b15abe38576f5c1323 authored over 3 years ago

docs: add eltociear as a contributor for doc (#339)

* docs: update README.md [skip ci]

* docs: update .all-contributorsrc [skip ci]

Co-authore...

a33e8c9c1bb236e6db8265fe66f4f8d4c950ca51 authored over 3 years ago

fix typo (#338)

* fix typo

* fix speller error

4ad2e337c15bcb45c24857336dbbeac981db5c78 authored over 3 years ago

docs: add ultradian as a contributor for doc (#335)

* docs: update README.md [skip ci]

* docs: update .all-contributorsrc [skip ci]

Co-authore...

3f7f914fe1dc5bebad6a0db66202219c936d6cbd authored over 3 years ago

correct spelling in FAQ (#334)

happends -> happens

675404f3daf052d29b1ef4b3a4dc1e8d4605b751 authored over 3 years ago

fix 332 (#333)

* fix 332

fix 332

* add missing using InteractiveUtils

b9e0b60088d869b2b698ddd51cf912c6325d958d authored over 3 years ago

CompatHelper: bump compat for "StructArrays" to "0.6" for package ReinforcementLearningZoo (#331)

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

89fa6704e653f66c93ca6456998db1b99b0152e9 authored over 3 years ago

Expand DDPG to multi action spaces (#330)

* Expand DDPG to multi action spaces

* Fix error

Fix dimension mismatch

3b7327fedb218674beb2122cb42ca268008175c9 authored over 3 years ago

Update doc string of PrioritizedDQNLearner (#329)

7f3da626300c2301ab48c7447eeda94a9435066c authored over 3 years ago

Add a warning in docstring of state (#327)

Address the concern in https://github.com/JuliaReinforcementLearning/GridWorlds.jl/pull/146#issu...

7671d8a0dea4988d24aa3d7e5da00c0ef609385b authored over 3 years ago

Fix broken test (#325)

* Fix broken test

* fix typo

ebd95191776c19b9b3da71d6f51cd0183e6d66f2 authored over 3 years ago

CompatHelper: bump compat for "GPUArrays" to "7" for package ReinforcementLearningCore (#322)

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-...

1318b51ff09d77a085de31a8b4d25648066972b1 authored over 3 years ago

Ecosyste.ms: OpenCollective

github.com/JuliaReinforcementLearning/ReinforcementLearning.jl