github.com/JuliaReinforcementLearning/ReinforcementLearning.jl commits

drop DomainSets.jl 0.7 from compat

168a5f3eec6478813804eadc412b0d239689a07d authored 11 months ago by Jeremiah <[email protected]>

Fix PPO per #1007 (#1013)

2e1af7f2d268b361aaef448092ff5626d52cb2d4 authored 11 months ago by Jeremiah <[email protected]>

Update Project.toml

98ebba3359d8176efb511c3097a680212c737524 authored 11 months ago by Jeremiah <[email protected]>

CompatHelper: add new compat entry for Parsers at version 2 for package ReinforcementLearningCore, (keep existing compat) (#997)

Co-authored-by: CompatHelper Julia <[email protected]>
Co-authored-by: Jeremia...

a1d87457c44059283776e1324fab3ae031baab19 authored 11 months ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

CompatHelper: add new compat entry for Statistics at version 1 for package ReinforcementLearningCore, (keep existing compat) (#999)

Co-authored-by: CompatHelper Julia <[email protected]>
Co-authored-by: Jeremia...

8df8dc1481d5aa173e7484855b4365748b1dc9b6 authored 11 months ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

CompatHelper: add new compat entry for MLUtils at version 0.4 for package ReinforcementLearningZoo, (keep existing compat) (#998)

Co-authored-by: CompatHelper Julia <[email protected]>

4a5a89365438f731969b96ba4c5d0223b6265a63 authored 11 months ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

CompatHelper: bump compat for DomainSets to 0.7 for package ReinforcementLearningBase, (keep existing compat) (#986)

Co-authored-by: CompatHelper Julia <[email protected]>

b7c6a0242292f0a2a944f95ec39584c228f1e62f authored 11 months ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Bump RLCore, RLEnv (#1012)

4c6912c0036390c73f1399b404bb47e52c9e15a2 authored 11 months ago by Jeremiah <[email protected]>

Make it compatible with Adapt 4 and Metal 1 (#1008)

091c5d474ca059e0e71283629cd4e8197872d2f0 authored 11 months ago by Joel Reymont <[email protected]>

Bump tj-actions/changed-files from 35 to 41 in /.github/workflows (#1006)

Bumps [tj-actions/changed-files](https://github.com/tj-actions/changed-files) from 35 to 41.
- ...

f574ecb6ed20ce9a8e6fc0c748e6b3a24a95af82 authored about 1 year ago by dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

Update CQL_SAC.jl (#1003)

ecadf3b8b1d8f0d9e5f4f8bb7d5a8e40bad54b1f authored about 1 year ago by Henri Dehaybe <[email protected]>

Conservative Q-Learning (#995)

* divide sac into functions

* bump version

* implement CQL

* create OfflineAgent (does ...

e1d9e9e21a0a3955667a1276b1140b3b72bf9d4b authored about 1 year ago by Henri Dehaybe <[email protected]>

CompatHelper: add new compat entry for IntervalSets at version 0.7 for package ReinforcementLearningExperiments, (keep existing compat) (#994)

Co-authored-by: CompatHelper Julia <[email protected]>

8f5ea30e3d2e4a47007a77a4350d550535adbbaf authored about 1 year ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

CompatHelper: add new compat entry for CUDA at version 5 for package ReinforcementLearningExperiments, (keep existing compat) (#991)

Co-authored-by: CompatHelper Julia <[email protected]>

34d5033fedb6ad5325a50ce4c9b53febe1d688fd authored about 1 year ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Fix and refactor SAC (#985)

* make softgaussian

* add tanh

* Update docstring

* fixing SAC

* enable tests

* I...

e772d6f8f048dce09305f8980a4b69d97abfdd33 authored about 1 year ago by Henri Dehaybe <[email protected]>

remove rlenv dep for tests (#989)

3b21982ca2a15bed6ad76cafd4699acffac93936 authored about 1 year ago by Henri Dehaybe <[email protected]>

Nfq refactor (#980)

* Mimic DQN interface

* Modify Experiment

* Remove GPU in experiment

* Change batch size

dd19ee094d8913ecc37127914c677da62f6e56d9 authored over 1 year ago by CasBex <[email protected]>

CompatHelper: bump compat for ReinforcementLearningCore to 0.13 for package ReinforcementLearningExperiments, (keep existing compat) (#977)

Co-authored-by: CompatHelper Julia <[email protected]>

3b301af27030fb62569f12dde6e87a9785761ed5 authored over 1 year ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

CompatHelper: bump compat for ReinforcementLearningZoo to 0.8 for package ReinforcementLearningExperiments, (keep existing compat) (#976)

Co-authored-by: CompatHelper Julia <[email protected]>

181f6dd0d4ac41aee396951365d48ca595ec54e5 authored over 1 year ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

CompatHelper: bump compat for ReinforcementLearningCore to 0.13 for package ReinforcementLearningZoo, (keep existing compat) (#975)

Co-authored-by: CompatHelper Julia <[email protected]>

46711262124772e8764e5054ee7bbeb3f45edc41 authored over 1 year ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Send relevant arrays to gpu (#974)

d7dba9bb16943e80ab1adddff86a04c36a710e9d authored over 1 year ago by CasBex <[email protected]>

TargetNetwork (#966)

* move learner stuff to learners.jl

* regroup includes

* move approximator

* docstring
...

3af751232dbddc76e7e17314d935a6e0063653d0 authored over 1 year ago by Henri Dehaybe <[email protected]>

CompatHelper: bump compat for GPUArrays to 9 for package ReinforcementLearningCore, (keep existing compat) (#969)

Co-authored-by: CompatHelper Julia <[email protected]>

4f414c625f4c38764e89b123f1c617ba0adb54f9 authored over 1 year ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

CompatHelper: add new compat entry for cuDNN at version 1 for package ReinforcementLearningExperiments, (keep existing compat) (#964)

Co-authored-by: CompatHelper Julia <[email protected]>

a8ae878a49901d7b748759739e8499f9f2d12a4f authored over 1 year ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

CompatHelper: add new compat entry for cuDNN at version 1 for package ReinforcementLearningZoo, (keep existing compat) (#963)

Co-authored-by: CompatHelper Julia <[email protected]>

6b3f0f78595fd28d667adcb0711ab3cc2a85f839 authored over 1 year ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

CompatHelper: add new compat entry for cuDNN at version 1 for package ReinforcementLearningCore, (keep existing compat) (#962)

Co-authored-by: CompatHelper Julia <[email protected]>

3bf6c80aeb1272115357fb93af1aff05cb57fd5f authored over 1 year ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Refactor TRPO and VPG with EpisodesSampler (#952)

* Change qpolicy default update stage

* Add a docstring

* qbasedpolicy dispatches on learn...

208cfb75c25ccb587b95b3a6e8647af8038b2e73 authored over 1 year ago by Henri Dehaybe <[email protected]>

Bump RLEnvironments version (compat fix)

f258a8425b6424a2a8e316cc4892f40bd1dc9a32 authored over 1 year ago by Jeremiah <[email protected]>

Bump RLExperiments version (compat fix)

a92833bf41d3144a9a01a5d8d51d32b3e8b7b7fd authored over 1 year ago by Jeremiah <[email protected]>

Bump RLZoo version (compat fix)

55202c3eb05c964da5a69b6d1666817e6041af3c authored over 1 year ago by Jeremiah <[email protected]>

CompatHelper: bump compat for ReinforcementLearningCore to 0.13 for package ReinforcementLearningExperiments, (keep existing compat) (#958)

ad1874f999fe99901522aba74f831fe4e5fb1c0b authored over 1 year ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

CompatHelper: bump compat for ReinforcementLearningCore to 0.13 for package ReinforcementLearningZoo, (keep existing compat) (#957)

eebc2e55a775c9bbdf85567b269694410c7b4ffd authored over 1 year ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

CompatHelper: bump compat for ReinforcementLearningCore to 0.13 for package ReinforcementLearningEnvironments, (keep existing compat) (#956)

1332da353035ad3809d9e40ecc9fd8f58865d5f9 authored over 1 year ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Update RLCore Version, Breaking Release due to dropped hook

153f9b59987f61f713c7e2930f653e7ac02854f0 authored over 1 year ago by Jeremiah <[email protected]>

Fix TotalRewardPerEpisode bug (#953)

f64a647e5bfcff53e8f610f549da7caaee24b5fa authored over 1 year ago by Jeremiah <[email protected]>

update docs to loop refactor (#955)

aa25d570cd66ed5068b3e7a0f3492190f96d422e authored over 1 year ago by Henri Dehaybe <[email protected]>

Bump RLCore version (#950)

abae05c358635a29c9e7c0311e3db5066d5de724 authored over 1 year ago by Jeremiah <[email protected]>

Reduce find_all_max allocations and increase speed based on chatgpt s… (#938)

* Reduce find_all_max allocations and increase speed based on chatgpt suggestion

* Use GPUArr...

75a6dab6640bda524ca23f076fb5dc781a7529fd authored over 1 year ago by Jeremiah <[email protected]>

Github Actions Fixes (#947)

* Go back to using julia-test

* Parallelize github actions

* version bumps

* Fix job na...

3d97a4fbfab16dd601adaeebdc41179956fd9933 authored over 1 year ago by Jeremiah <[email protected]>

CI Improvements (#946)

5db57bb52e9e50bcbe39c4624ad715ef72271406 authored over 1 year ago by Jeremiah <[email protected]>

Drop deprecated @provide interface (#944)

* Drop deprecated @provide interface

* Temporarily disable experiment

82bcbe1154824d03af96c2e40c2cab46bddcfce0 authored over 1 year ago by Jeremiah <[email protected]>

Add RLZoo and RLExperiments to Buildkite (#943)

* Add RLZoo and RLExperiments

* Repair pipeline metadata

* Add mac/windows to GH Actions CI

01b0121e3dabf08e2621c3455a994a7a72c4dad3 authored over 1 year ago by Jeremiah <[email protected]>

Add encrypted codecov token

6988f717cd5bbe3a269b472feacd410a4f7a260a authored over 1 year ago by Jeremiah <[email protected]>

Move pipeline.yml to .buildkite

899bbe93afa9f351464f2319a976e6947c593f4e authored over 1 year ago by Jeremiah <[email protected]>

Add Buildkite / GPU tests (#942)

bf5934e9a195ee3b77085afd569d333596e3f6ba authored over 1 year ago by Jeremiah <[email protected]>

Update Project.toml

12a9a856106d73880d19d6b204db59a3f7030271 authored over 1 year ago by Jeremiah <[email protected]>

RLEnvs Version bump

2df88c77064f3604108ce5e7f27f69b0e07ca19a authored over 1 year ago by Jeremiah <[email protected]>

Rework the run loop (#921)

cce387ba27640673eac0b038bb6c18be44603bf2 authored over 1 year ago by Henri Dehaybe <[email protected]>

Version bumps

27524207d794ed6c21d2429b886313b143c67c27 authored over 1 year ago by Jeremiah <[email protected]>

Bump flux compat (#935)

dfc2f82dd9bad0caf4afceee9b80093075ed1888 authored over 1 year ago by Jeremiah <[email protected]>

fixed devmode / project files (#932)

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

102e35f71f9db456783e60822484b9b049a36848 authored over 1 year ago by Mytolo <[email protected]>

fixing prob. /w symbol/ string correspondence (#934)

Co-authored-by: Jeremiah <[email protected]>

920220244a2b9328107b7cba167b84749813e65a authored over 1 year ago by Mytolo <[email protected]>

fixed DQNLearner Gpu isse (#933)

* fixed DQNLearner Gpu isse

* reanme variables for cspell / conventions

bd78e83cfdf0f42abba50b295187970e22a1b3fb authored over 1 year ago by Mytolo <[email protected]>

adjusted pettingzoo to PettingZooEnv simultaneous environment more convenient (#925)

1f7f3479701b64b0b8788c76743937b39192c7fc authored over 1 year ago by Mytolo <[email protected]>

couple of improvements (#919)

3182026e9352d4c1d5b27391ed95dcf72f6461f6 authored over 1 year ago by Henri Dehaybe <[email protected]>

Fix Timer bug (#915)

* Fix variable naming

* Bug fix version bump

* Add debug test

* Add import statement

b54a0b0e66e21331808fa72629f08676d8b4809e authored over 1 year ago by Jeremiah <[email protected]>

Add compat for TimerOutputs.jl

038b59edb312195d2497892a5727dae06c56e4b9 authored over 1 year ago by Jeremiah <[email protected]>

Bump version RLCore to v0.11.1

9e60c803e3e1b892ea83dfc4ad0a5a451b562a4a authored over 1 year ago by Jeremiah <[email protected]>

Add performance testing run loop (#914)

91d80e97af49518e7d1ec7218371e7b2c53510cb authored over 1 year ago by Jeremiah <[email protected]>

NFQ (#897)

* NFQ before refactor

* NFQ after refactor

* Move to dqns

* Refactor

* Add NFQ to RL...

72d67668f52ea45e90ee79b0a3a33055cce8cef7 authored over 1 year ago by CasBex <[email protected]>

QBasedPolicy optimise! forwards to learner. (#909)

* Change qpolicy default update stage

* Add a docstring

* qbasedpolicy dispatches on learn...

6de371fa9f1c3c71348b3842e3fddb18825c2e39 authored over 1 year ago by Henri Dehaybe <[email protected]>

Bump version NNlib (#911)

2e229d81e1c08a86acb4a2193c8d77806c917967 authored over 1 year ago by Jeremiah <[email protected]>

CompatHelper: bump compat for NNlib to 0.9 for package ReinforcementLearningZoo, (keep existing compat) (#906)

Co-authored-by: CompatHelper Julia <[email protected]>
Co-authored-by: Henri D...

2c96936c26da91bfcd1aa22c3f84f01fb8520826 authored over 1 year ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Fix dispatch and update documentation (#907)

* default optimise is nothing

* Qbased is dispatched on traj

* rem some abstract field typ...

e072b4b13b4249ac543d86911b14a846a61f57aa authored over 1 year ago by Henri Dehaybe <[email protected]>

Swap out rng code (#905)

62e6e38facabd49c579c8bad56a272bbdbca8579 authored over 1 year ago by Jeremiah <[email protected]>

Bump version for compat bump

7e3cbc3356fe874a4e664e185fff5d59ca875a73 authored over 1 year ago by Jeremiah <[email protected]>

Breaking changes to optimise! interface: Bump RLCore to v0.11 and RLZoo to v0.8 (#903)

a702dc6abec70ba63df132a03abff8ad6e297629 authored over 1 year ago by Jeremiah <[email protected]>

Bug fix optimise! (#902)

cf94360c79e0212c312c738a088c3041c83186b6 authored over 1 year ago by Jeremiah <[email protected]>

Sketch out optimise! refactor (#899)

ea00fdfc0cc4cae92013211d63767bc081b2b603 authored over 1 year ago by Jeremiah <[email protected]>

fixed problem with sequential multi agent envs (#898)

fdcb1b8e2fa897121073d24d9a2a02d8791b7be8 authored over 1 year ago by Mytolo <[email protected]>

Update implement new alg docs (#896)

57ef3a9de351deb64e85c4bed1a772d1ce10872b authored over 1 year ago by Jeremiah <[email protected]>

CompatHelper: add new compat entry for DelimitedFiles at version 1 for package ReinforcementLearningEnvironments, (keep existing compat) (#894)

Co-authored-by: CompatHelper Julia <[email protected]>

5359abd2a392394b52ac9d6df87b4d8b38f4b994 authored over 1 year ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

allow more recent versions (#890)

* allow more recent versions

* Update Project.toml

---------

Co-authored-by: Jeremiah <...

f7fdb1427540aa2c73cdc7a60702a5ffa6ad7d3e authored over 1 year ago by Henri Dehaybe <[email protected]>

Fix stack (#891)

* Update Flux.stack

* julia compat

* zoo compat

* Experiments compat

75982370ce656b7f38b25d8f2984b0424c01aaa3 authored over 1 year ago by Henri Dehaybe <[email protected]>

Stacknamespace (#889)

03b10e694a8f70b598d6c5359436d2d5b67ceb04 authored over 1 year ago by Henri Dehaybe <[email protected]>

CompatHelper: bump compat for ReinforcementLearningZoo to 0.6 for package ReinforcementLearningExperiments, (keep existing compat) (#888)

* CompatHelper: bump compat for ReinforcementLearningZoo to 0.6 for package ReinforcementLearnin...

dd32beb20a3725cb3e8aba8568bcc4967498ebb6 authored over 1 year ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Fix hook issues (#887)

* Fix hook issues

* Drop is_terminated check from run function

* Version bump

* Update ...

050349688a055ce05eb98f9fa8640685f7602042 authored over 1 year ago by Jeremiah <[email protected]>

Add compat for CommonRLInterface (#886)

6797f8936c0e5524dc8c2a234ea2c4b0cc6a6a01 authored over 1 year ago by Jeremiah <[email protected]>

Use multiple dispatch / methods plan! and act! and push! (#880)

* Agent SRT Cache Performance Optimizations

* Fix hook type signature?

* Try returning not...

395f23fa94e1f5d5dba342c19feb7b4f892030d1 authored over 1 year ago by Jeremiah <[email protected]>

Further refinements (#879)

* Don't use generator

* Tweak TotalRewardPerEpisode type creation

* revert

* Add missin...

a91ec1f470c036dc7cdb37fcd91c686a84ccc1a3 authored over 1 year ago by Jeremiah <[email protected]>

Add back ComposedStop (#876)

* Add back ComposedStop

* Fix export

* Fix test

* Update src/ReinforcementLearningCore/...

6cb9449b134f4c67731cc46bd50fd48cda9ee86d authored over 1 year ago by Jeremiah <[email protected]>

Fix RLEnvs compat (#875)

* Lower bound RLCore compat

* Compat fix

* Fix RLEnv Compat

* Fix RLBase compat

* Bu...

9961fe66bda28cebe47933a40db3fd3f27b38a2f authored over 1 year ago by Jeremiah <[email protected]>

Bump RLBase to v0.11.1 (#877)

* Bump RLBase to v0.11.1

* Fix test

af2b158b9276c6960bf152839aa571572f4ed88a authored over 1 year ago by Jeremiah <[email protected]>

ComposedHooks, MultiHook fixes (#874)

18714fc5cc13cab9c77e31f01c4acb5d7d1d97a4 authored over 1 year ago by Jeremiah <[email protected]>

Bump StatsBase compat (#873)

6653304cb7a76b28f598f32ab636194da0030319 authored over 1 year ago by Jeremiah <[email protected]>

Added a section to the home page about getting help for ReinforcementLearning.jl. (#868)

5c9994173a55dc1c4c4aa4d799312d4bed503fb0 authored over 1 year ago by Steven Lohrenz <[email protected]>

Multiplayer Fixes (Clean up errors) (#867)

* apply patches

* Missing @

* Update release notes, bump versions

* Fix type syntax

afc42f0c33f046a5532bbc57446a2cc1504bf54b authored over 1 year ago by Jeremiah <[email protected]>

CompatHelper: add new compat entry for ReinforcementLearningCore at version 0.9 for package ReinforcementLearningEnvironments, (keep existing compat) (#865)

Co-authored-by: CompatHelper Julia <[email protected]>

bdae1a2ba109536d4e84889668e0c7d09452d6b6 authored over 1 year ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

MultiAgent Proposal (#861)

* add scrap

* broken, but moving forward

* tweaks

* more tweaks

* rough sketch now w...

5143f60ccbe788eaf7e8aff3282b3fd1d1e32f2a authored over 1 year ago by Jeremiah <[email protected]>

CompatHelper: bump compat for FillArrays to 1 for package ReinforcementLearningCore, (keep existing compat) (#859)

* CompatHelper: bump compat for FillArrays to 1 for package ReinforcementLearningCore, (keep exi...

e2da341a12d74edaa5348866684c02421f77c1d4 authored almost 2 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Tweak CI to check on dep changes (#858)

* Check on dep changes

* useless change

* remove useless

* CI on latest julia

* Reve...

8260b3d79be17585172b12a373e1cba01b80a048 authored almost 2 years ago by Henri Dehaybe <[email protected]>

update CI Julia version (#857)

6c395ca48356369db3aa20e373d681b7ef2ef804 authored almost 2 years ago by Jeremiah <[email protected]>

Include codecov in CI (#854)

* Include codecov in CI

* Update ci.yml

* Tweak codecov

* [test] ski...

db5d23b352ff0ba1caa921d58a92ed285fd6eae7 authored almost 2 years ago by Henri Dehaybe <[email protected]>

DoEvery should not trigger on t = 1 (#856)

* DoEvery should not trigger on t = 1

Currently, DoEvery hooks trigger at the first step (bec...

8392505a89310e9286c5d469994663942eeb1a80 authored almost 2 years ago by Henri Dehaybe <[email protected]>

Fix a typo in MPO (#855)

* Update mpo.jl

* remove a problematic modulo

fb8ad51224f0345d780e9edce4dde9cf8f6ed183 authored almost 2 years ago by Henri Dehaybe <[email protected]>

Gaussian network refactor and tests (#849)

* Refactor with sigma instead of logsigma

* Rewrite 3D CovGaussianNet sampling

* update VA...

74501b753ea84f6186c1bc426200794fe1e24da4 authored almost 2 years ago by Henri Dehaybe <[email protected]>

Bump RLCore (#851)

dae8437888ca48701b686a5f67e35d20dc7ab375 authored almost 2 years ago by Jeremiah <[email protected]>

Agent Refactor (#850)

* Add subfolder

* Fix typo

* Begin refactor

* Further tweaks

* Add update_reward!

...

23da24c22df57919cbce95ffce4c4991c9159900 authored almost 2 years ago by Jeremiah <[email protected]>

Add activate_devmode!() explanation to tips.md (#845)

9faa8fb9b63d6d4c46a1515afdde54e3299b515a authored almost 2 years ago by Jeremiah <[email protected]>

add kwargs to agent (#847)

* add kwargs to agent

* Update NEWS.md

* Docstring

* Add agent tests

b1be8040f5df2f42711d1fa4028d72643ee2b733 authored almost 2 years ago by Henri Dehaybe <[email protected]>

Ecosyste.ms: OpenCollective

github.com/JuliaReinforcementLearning/ReinforcementLearning.jl