github.com/JuliaReinforcementLearning/ReinforcementLearning.jl commits

Reactivate docs (#842)

* Reactivate docs

* Fix config.json

* basic fixes

* Spaces in paths

* Try path fix
...

29cdce8898070c9193d0e9b86e588e0895171ec8 authored almost 2 years ago

Bump compat of RL.jl to 0.11.0-dev (#846)

28a76e65be7787b0b1da34890fab7c49cbbb19ec authored almost 2 years ago

Make TimePerStep test robust (#841)

* Make TimePerStep test robust

* Refix tests

* Update hooks.jl

13e15fe43dd66362dc70aad0e256be203dd6ac2c authored almost 2 years ago

Add test_noop! to remaining hooks (#840)

* Add test_noop! to remaining hooks

* Add docstring

* Fix tests

be0bfd1b93d9c565453e8a8bcdb2a78c7ee85645 authored almost 2 years ago

Fix branch name (master -> main) (#837)

* Fix branch name (master -> main)

* Fix branch triggers

a481a704507d8be01facebdad63edead3bc71991 authored almost 2 years ago

Refactor and add tests to TotalBatchRewardPerEpisode (#830)

* Make TotalRewardPerEpisode immutable

* tweak struct

* Simplify TotalBatchRewardPerEpisod...

41f86dcebd370e8b3d61d6570280554dcd4fe598 authored almost 2 years ago

Expand PR Template (#835)

* Expand PR Template

* Update .github/pull_request_template.md

d9025546b0a152b38f84d886b0d4a4201a0d5db0 authored almost 2 years ago

Add DoOnExit test (#833)

* Fix test

* Fix tests

* Format code

* Add DoEveryNEpisode

* code format

291b7f5f7d0f22a4f37a8cbaf51948b0f1c32a75 authored almost 2 years ago

DoEveryNStep tests, performance tweaks (#832)

12995f284564ecde4a7d71aa91683997739cebde authored almost 2 years ago

Tests, refactor for TimePerStep (#831)

f57f2dad3bb21c2435fc821a5c06164a6002d01b authored almost 2 years ago

Add tests, improve performance of RewardsPerEpisode (#829)

* Add tests for StepsPerEpisode

* Add hook tests, minor performance tweaks

* update news
...

856e056641a1b4d45aaa3a1536151cacb85417a9 authored almost 2 years ago

Basic allocation fixes for RandomWalk / RandomPolicy (#827)

* Basic allocation fixes for RandomWalk / RandomPolicy

* Drop incorrect dependency

* Expan...

11f96deace1b64d9f551b1db315428ce3f03ef80 authored almost 2 years ago

Bump CI.yml GitHub action versions (#828)

674b917bf299b4d034bad63b24465862edb45ac5 authored almost 2 years ago

Bump Github Actions cache version (#825)

6f944ebcccef3cade40eb5d8519554c4cc694ef1 authored almost 2 years ago

Merge pull request #824 from JuliaReinforcementLearning/jeremiahpslewis-patch-7

Drop RL.jl from CompatHelper (until refactor complete)

cac2c2b0d63bb02f1abe369330d0fd33ea8de81c authored almost 2 years ago

Drop RL.jl from CompatHelper (until refactor complete)

92351e4297c87bbd89f6557ed596a021c7568065 authored almost 2 years ago

Pin ReinforcementLearningZoo.jl to 0.6 in RLExperiments

25d9349c9fe20956419ea6341baf01a7237361bf authored almost 2 years ago

Merge pull request #818 from JuliaReinforcementLearning/jeremiahpslewis-patch-5

Bump RLExperiments, require 0.11

d40dde1d4804965265eb9eeabab2fec500f2f490 authored almost 2 years ago

Bump, require 0.11

0537276ff77a0774215388127f1d1c71a33ea118 authored almost 2 years ago

Expand RLZoo compat (#817)

589fa9efc8130372bbde0f2733dbaf3ab68f15e0 authored almost 2 years ago

Fix RLExperiments compat (#816)

949029276472efb9d80e886d8f3bc64246264b4a authored almost 2 years ago

Merge pull request #815 from JuliaReinforcementLearning/jpsl-rlzoo-0.6

Bump RLZoo.jl version for release

ce2dd4558846ceef644cc25c41297e87e7c8aae7 authored almost 2 years ago

add news.md

c7d97ba6d855513e9820271f25694fdbc2fa2b1b authored almost 2 years ago

Bump RLZoo.jl version for release

c3eacecf70f228aa4efb78ce328f95865557b21f authored almost 2 years ago

Fix IntervalSets compat (#800)

9b1c2737044736d642d54b10917b038cd5f0bd73 authored almost 2 years ago

Bump compat helper (#799)

* Bump compat helper

* Fix subdirs

bbce4f10c1863b3cae4a98f0a0b1595c34606342 authored almost 2 years ago

Add reexport compat (#798)

d49bdd226ccc7e89ec0ebf8eaffee245a5e94346 authored almost 2 years ago

Merge pull request #797 from jeremiahpslewis/jpsl-bump-RLCore

Fix RLCore version, prep for bump

a6216b0b6e21fda86b72611228698455ce515b22 authored almost 2 years ago

Fix RLCore version, prep for bump

98601bdb760d2932933571a0097c4d705e82802e authored almost 2 years ago

Fix compat for RLBase (#796)

b38b9f30c5750bc0d522f423d910750efb6f507b authored almost 2 years ago

Reactivate some tests for RLExperiments (#790)

* Reactivate some tests for RLExperiments

* Update ReinforcementLearningExperiments.jl

107ceec40976d8023bc2b17a82861e4a240b7dee authored almost 2 years ago

Merge pull request #795 from jeremiahpslewis/jpsl-dropRL_jl-from-experiments

Drop RL.jl as dependency from Experiments

0457c81f483fa69d27cf0ead48c1c98f5e2a02d6 authored almost 2 years ago

Swap out import statement

fbae41482bb1330f150e8bd9dd0067602935c4a5 authored almost 2 years ago

Add RLEnv import where necessary

090ad767f3169e09e83fab8fb2f2bc69d34e0b58 authored almost 2 years ago

Update Flux Adam call syntax

53aeffe1abefaa926881b6aa383a55f9e3936441 authored almost 2 years ago

Make Experiment call to RLCore. from RL.

10ed976efdb779e9a0004d5797314f5087dc4b72 authored almost 2 years ago

Fix pkg name, call

a76537589f99bb5d208de0e53f24186795595c82 authored almost 2 years ago

Drop RL.jl from experiments CI

902e11268fea68dad54427d4b637f8cee3c48d19 authored almost 2 years ago

Bump news

654e9158429864c7e12660a8eeec651f1e442935 authored almost 2 years ago

Drop RL.jl as dependency from Experiments

c0e8aa2ac635124184add18d8fc9346524d10a24 authored almost 2 years ago

Merge pull request #794 from JuliaReinforcementLearning/jeremiahpslewis-patch-1

Update TagBot.yml

f5a7144897511a5be2019e86d19a81cf4cfd07d4 authored almost 2 years ago

Update TagBot.yml

495560da43c9be2e58aa8f21c38f010343213a1b authored almost 2 years ago

Pin ReinforcementLearning.jl to pre-refactor versions (#793)

* Tag 0.10.2 version

* Update NEWS.md

d1971f5719474c82bdafdbfa503434cffffafc10 authored almost 2 years ago

Temporarily disable failing experiment so project tests pass (#787)

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

01f264c43c06e48b92b959a09e70151c8e8cc3d8 authored almost 2 years ago

Fix spellcheck errors (#788)

* Fix spellcheck errors

* Extend spellcheck allowlist

---------

Co-authored-by: Jun Tia...

c88a1ae25927352686f8418a5d4660c18d626845 authored almost 2 years ago

Bug fixes and dependency bump (#789)

* Update RLBase dependency name

* Update news.md

* Use new Flux.stack syntax based on MLUt...

f761874f262d213caafa82fabedf762c3685312e authored almost 2 years ago

Reduce unnecessary array allocations (#785)

* Reduce unnecessary array allocations

* Add news.md comment

8f71367fe22256c77934b722a75f7d63537be893 authored almost 2 years ago

Update mpo.jl (#783)

8a46bfb77e382d9304e45c00051c67e3b9949e85 authored almost 2 years ago

added pettingzoo and one single agent example (#782)

Co-authored-by: Panajiotis Keßler <[email protected]>

8e2af68f2e74c6360f4323fc6cc16d9fe8fd167f authored almost 2 years ago

Add MPO in zoo (#604)

* various changes

* improve SAC docstring

* SAC: add target network and start policy defau...

b9d0ee0bffc0b64b71f6324ca28db3d06a3098aa authored about 2 years ago

Merge pull request #777 from JuliaReinforcementLearning/devmode

Add a developer mode

9c832f6561211cb70556905827fc03fb00cbf3a3 authored about 2 years ago

fix cspell

b3e6841ae41e40e21cfe7b9b4e5f74bceaca68cc authored about 2 years ago

add a docstring

4483b2d7a9ebfc664a5124d391ebb96b29d144b8 authored about 2 years ago

Add devmode

3ffb51f69974e320a259e07be014eda330abcbbe authored about 2 years ago

Merge pull request #776 from JuliaReinforcementLearning/experiments

Uncomment experiments that were broken

107918482eaaf1c9d3fed4143b03be66c4d286a4 authored about 2 years ago

uncomment other exps

a6d68c0c3cde77e0f8ee2790b7c0edbe17b5a775 authored about 2 years ago

implement missing player argument

6ff28119fb1c24e911b7433b827a6579ad1d3e8c authored about 2 years ago

uncomment exp

819ebfe23b2317a471d540b7bf442ddc9c3d4441 authored about 2 years ago

Merge pull request #775 from JuliaReinforcementLearning/dependencies

fix compat

77203a6ba1e08ced10bda7f4ac738cd2734ba1bb authored about 2 years ago

Merge branch 'master' into dependencies

16ed98538e86f3ae7b68bead96bf53fcaadcdda6 authored about 2 years ago

fix namespace

e2d8c031399d3ab9252deef6157ddf6f0f01b4e4 authored about 2 years ago

import ChainRulesCore in test

a6fc017c9043f7354930e4f58d9d5fc68e5f2a09 authored about 2 years ago

fix compat

9fce4e1d8997e285feb3a8594722fb58579d929f authored about 2 years ago

Merge pull request #774 from JuliaReinforcementLearning/update-Flux-namespace

import params and gradient

25a83df11fc0334cad2df7db1c0041b046c6b92e authored about 2 years ago

typo

90a74c3e7a1374db6ff1dd98f32d883dd6a42916 authored about 2 years ago

Merge branch 'master' into update-Flux-namespace

2a57cfe92e236d215ded31d5afe59671b459d4c2 authored about 2 years ago

import params and gradient

f0194ad22b9104484a9742dde55b2d2220f50d9e authored about 2 years ago

Merge pull request #748 from JuliaReinforcementLearning/compathelper/new_version/2022-08-18-00-53-06-886-2420228405

CompatHelper: bump compat for "CommonRLSpaces" to "0.2" for package ReinforcementLearningBase

eeb7fc1b0b498280f7753e04b0ae253a51c7f0dc authored about 2 years ago

add dep

55f7aac43b68b16f226ed79f093c09224123dbb5 authored about 2 years ago

Merge branch 'master' into compathelper/new_version/2022-08-18-00-53-06-886-2420228405

60816c32bbd5713ba1d80f043f6a3bd5855e7c27 authored about 2 years ago

Merge pull request #773 from JuliaReinforcementLearning/master

Remove manifest from the repo

cb3882e496fa1932bfbca12f5ec886e8e4c8a5cc authored about 2 years ago

fix unresolvable requirements

5448b9fcdf3e2ee917af6b60bd6e537f75db98f8 authored about 2 years ago

remove deps

f7b9db5ca52bdc2ea01e18aecaa5a4916d5a625c authored about 2 years ago

ignore subpackages manifests

c7666ccea1a17cb38ef670911bf262c6847bfebf authored about 2 years ago

remove manifest

99af1540a27b1bac50542c18b85e4a85889b161f authored about 2 years ago

ignore manifest and dev subpackages

ac94d5e09abc4d852bc1be1216eef9a11813ea91 authored about 2 years ago

Merge branch 'master' into compathelper/new_version/2022-08-18-00-53-06-886-2420228405

214548b24bc09c3c9758edd4a88e6ca1a778197a authored about 2 years ago

Merge pull request #723 from JuliaReinforcementLearning/compathelper/new_version/2022-07-02-00-49-49-851-1149465711

CompatHelper: bump compat for "ReinforcementLearning" to "0.10" for package ReinforcementLearnin...

94b60ae04087ddeca7fce536c2d4a8484b9d19d9 authored about 2 years ago

Merge branch 'master' into compathelper/new_version/2022-07-02-00-49-49-851-1149465711

4e9c21f9037dad2db44b346447de2beb9abbdde4 authored about 2 years ago

Merge pull request #722 from JuliaReinforcementLearning/compathelper/new_version/2022-07-02-00-49-42-702-607058433

CompatHelper: add new compat entry for "StableRNGs" at version "1" for package ReinforcementLear...

caf87863091bf5f8a08d7ce0ea93d54ab17ed360 authored about 2 years ago

Merge branch 'master' into compathelper/new_version/2022-07-02-00-49-42-702-607058433

a1ecc24f9b222528865dacbfec294262dc0e76b6 authored about 2 years ago

Merge pull request #721 from JuliaReinforcementLearning/compathelper/new_version/2022-07-02-00-49-28-857-1483723495

CompatHelper: bump compat for "Functors" to "0.3" for package ReinforcementLearningZoo

286b77eb79efd5a056f7845f2517f6e35192d2ff authored about 2 years ago

Merge branch 'master' into compathelper/new_version/2022-07-02-00-49-28-857-1483723495

54442ec9e84c80dcc5eda48066efa17500879977 authored about 2 years ago

Merge pull request #720 from JuliaReinforcementLearning/compathelper/new_version/2022-07-02-00-49-22-022-3734735542

CompatHelper: bump compat for "ReinforcementLearningCore" to "0.8" for package ReinforcementLear...

7e7bcd0e95e5ba3cecaebe21394a07703c8f6e7c authored about 2 years ago

Merge branch 'master' into compathelper/new_version/2022-07-02-00-49-22-022-3734735542

4e6c3dd4f8528bf3d6fa32e063ae7429856af6ae authored about 2 years ago

Merge pull request #771 from JuliaReinforcementLearning/HenriDeh-patch-1

RLZoo: Bump RLBase compat to 0.11

0b27e23a71de6b6c20d5fc1b9f09ace3d51aed7a authored about 2 years ago

Update runtests.jl

505afa427c0e6e25e8f02166cb5620cdeb03d0d7 authored about 2 years ago

Update Project.toml

c39c37ab7fe6006003ae52e52025f83a446c3018 authored about 2 years ago

Update Project.toml

180c934509e9e5cac662f71b0b6999eafa1d9308 authored about 2 years ago

Merge branch 'master' into compathelper/new_version/2022-07-02-00-49-49-851-1149465711

f24c250273cc38b71f1740a379d96e597d7cf8f4 authored about 2 years ago

Merge branch 'master' into compathelper/new_version/2022-07-02-00-49-28-857-1483723495

b42841f5100d850bb21792ed65a2d904d8861afc authored about 2 years ago

Merge branch 'master' into compathelper/new_version/2022-07-02-00-49-22-022-3734735542

3f8c0ca9097b0bd2da0d16ad9b180ffe603a6717 authored about 2 years ago

Merge pull request #717 from JuliaReinforcementLearning/compathelper/new_version/2022-07-02-00-48-47-579-1590247915

CompatHelper: bump compat for "Functors" to "0.3" for package ReinforcementLearningCore

1ba32d938a9dc34e03cbf7e4bad58fc05ab2595d authored about 2 years ago

Merge branch 'master' into compathelper/new_version/2022-07-02-00-48-47-579-1590247915

fee157a846a031037a3851dcea7cfd9c57b8bf93 authored about 2 years ago

Merge pull request #715 from JuliaReinforcementLearning/compathelper/new_version/2022-07-02-00-48-26-524-287112613

CompatHelper: bump compat for "AbstractTrees" to "0.4" for package ReinforcementLearningBase

9edd2068bb2ef025660f6f9786b071b194fd95c3 authored about 2 years ago

Merge branch 'master' into compathelper/new_version/2022-07-02-00-48-26-524-287112613

1e73abe100a4e5178f00076a087debdbd9eac9f6 authored about 2 years ago

Merge pull request #713 from JuliaReinforcementLearning/compathelper/new_version/2022-07-02-00-48-05-956-1739709025

CompatHelper: bump compat for "ReinforcementLearningEnvironments" to "0.6"

873bde44e7b09cb4147bf79f555fa5927f18c45b authored about 2 years ago

Merge branch 'master' into compathelper/new_version/2022-07-02-00-48-05-956-1739709025

313ca45a821f94956bf1e9141b0b74a125fccb54 authored about 2 years ago

Merge pull request #712 from JuliaReinforcementLearning/compathelper/new_version/2022-07-02-00-47-57-468-670482445

CompatHelper: bump compat for "ReinforcementLearningCore" to "0.8"

207ae40f9e9a6cf8102f78f20c5daeca27b092f2 authored about 2 years ago

Merge pull request #718 from JuliaReinforcementLearning/compathelper/new_version/2022-07-02-00-48-54-515-3447723428

CompatHelper: bump compat for "UnicodePlots" to "3" for package ReinforcementLearningCore

2761f215704411f8863e72840e7103f17b1ecfa7 authored about 2 years ago

Ecosyste.ms: OpenCollective

github.com/JuliaReinforcementLearning/ReinforcementLearning.jl