github.com/JuliaReinforcementLearning/ReinforcementLearning.jl commits

Merge branch 'master' into compathelper/new_version/2022-07-02-00-47-57-468-670482445

e512a15e38f0ef42842453b8515bfd27729aaffb authored about 2 years ago

Merge branch 'master' into compathelper/new_version/2022-07-02-00-48-54-515-3447723428

89f237014ffe2f3aaca673c8e11b508041d26f08 authored about 2 years ago

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

13740a754dec507d30450d9bdebf3c2f83335a91 authored about 2 years ago

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

4f62eca42fad2a7b2924e761c898613ec722b8f2 authored about 2 years ago

Merge pull request #714 from JuliaReinforcementLearning/compathelper/new_version/2022-07-02-00-48-12-639-2417100009

CompatHelper: bump compat for "ReinforcementLearningZoo" to "0.5"

4f12d3674abd2e6ef441d0f3dbfc68ef5de91a10 authored about 2 years ago

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

1042146a2188403aa651de8661009045f2b97e86 authored about 2 years ago

Merge branch 'master' into compathelper/new_version/2022-07-02-00-48-12-639-2417100009

2a927aa8d7e6d56e28eaf61ad4c9f5a8fc2998c1 authored about 2 years ago

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

67f04f0b10aa005ba8fcada58e51a2b1328d6bb0 authored about 2 years ago

Merge branch 'master' into compathelper/new_version/2022-07-02-00-47-57-468-670482445

31f7179e9cdaa25662ad817f3090a642ad091f67 authored about 2 years ago

Merge pull request #768 from jeremiahpslewis/patch-2

Fix typo

6a050e000f6f9dd77311a7671ef8851478e247d0 authored about 2 years ago

Merge branch 'master' into patch-2

589c04d7232e83ea5cdd980e6690416a1af0d66f authored about 2 years ago

Merge pull request #767 from jeremiahpslewis/patch-1

Fix typo

7cc083a3ba2cfe6f4713edd2e518002b1fb718a1 authored about 2 years ago

Merge branch 'master' into patch-2

3b75c36a93d12b61cba53ed3b6b49ef08f06866b authored about 2 years ago

Merge branch 'master' into patch-1

e3621a0e4d296477d4894ea6a72f7753b9b98709 authored about 2 years ago

Fix TD Learner so that it handles MultiAgent/Simultaneous with NoOp (#769)

d20c431d722997aa49ff85fef5e3800ae71477a3 authored about 2 years ago

Fix typo

a611e61e76faf0411fda3c75bf6ab2ce63347f81 authored about 2 years ago

Fix typo

8bf51194d6857d18a1a8e2d3f0a2cd64e1b4d014 authored about 2 years ago

CommonRLSpace -> DomainSets (#756)

* CommonRLSpace -> DomainSets

* fix spell check

f97747923c6d7bbc5576f81664ed7b05a2ab8f1e authored over 2 years ago

TRPO (#747)

* implement `action_distribution`

* fix prediction

* fix spelling

* working

* add tr...

0a344ce4926d8ceb5ca9bc1ae9d82a15a0992946 authored over 2 years ago

docs: typo in hooks docs (#754)

b6efb1d6d58fa37f8b175cbd36014b6514d7e28d authored over 2 years ago

Update TwinNetwork (#752)

35c27e7ffcf4264b731f31d53d187531f27f4368 authored over 2 years ago

docs: add ludvigk as a contributor for code (#751)

* docs: update README.md [skip ci]

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

Co-authore...

6dedd904e062add919225b3d66618b5d06ba89e1 authored over 2 years ago

Update DoEveryNEpisode hook to new api (#750)

DoEveryNEpisode hook was called with stage=POST_EPISODE_STAGE as default rather than PostEpisode...

c8d7a0259f4065c3eb9a61c97d13012367db2b83 authored over 2 years ago

Fix parameter names for AsyncTrajectoryStyle (#749)

When using AsyncTrajectoryStyle, optimise! was called with p and t as parameters rather than pol...

746579de994bfa73d5d90071f12164589e4ede46 authored over 2 years ago

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

ee1ba64a932d1d408a5f4cb4ee21336925b4134b authored over 2 years ago

Update FUNDING.yml

c60cbb7048ed31178f1be727e938a9db41fdb3eb authored over 2 years ago

Create FUNDING.yml (#746)

6c5863f613c74574dd52e1d5470f492eedcf2abe authored over 2 years ago

docs: add mplemay as a contributor for doc (#743)

* docs: update README.md [skip ci]

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

Co-authore...

cd92f2d7d201c3569c1d5e5a8a8691bfe5c490d8 authored over 2 years ago

fixed hyperlink in readme (#742)

5685daed99bdb56a997dfdb4f9814dd801b9674e authored over 2 years ago

CompatHelper: add new compat entry for "Distributions" at version "0.25" for package ReinforcementLearningExperiments (#735)

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

c74f71711c11a36771700f21a94059ff367fbd35 authored over 2 years ago

CompatHelper: add new compat entry for "Distributions" at version "0.25" for package ReinforcementLearningZoo (#734)

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

6aed5a0154165091d149bf379576e85d6102303c authored over 2 years ago

add VPG (#733)

* add VPG

* update dependencies

f3c02abbf42ed0f7fc4e0a5fd6f95adeb2dec528 authored over 2 years ago

Add struct view (#732)

* support colorful struct view

02ceac44a1920292ee4bed2dc12dc4eaacf6e931 authored over 2 years ago

Merge pull request #726 from BigFood2307/multi_env_sac

Adapted SAC to support MultiThreadedEnv

20780df3f4be81da359214054e24f2c8d22ecece authored over 2 years ago

Merge branch 'master' into multi_env_sac

48d777732e801795f901a8eea2ac92bf6e30aa65 authored over 2 years ago

SAC: avoid splat and permutedims

9a6fee0142e789ad4a61bea5e1cde2b4f8cdc777 authored over 2 years ago

docs: add ll7 as a contributor for doc (#728)

* docs: update README.md [skip ci]

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

Co-authore...

318f0f1d2868adcb96050fbfe5894509287a3d37 authored over 2 years ago

Add the number of episodes (#727)

I think the variable `n_episode` should be defined, s.t. the example does run by copy and pastin...

5e55865b9ec056d6281338f6f02cced391080186 authored over 2 years ago

Adapted SAC to support MultiThreadedEnv

94b3ac4b08248093b9fbcd2602630ce22cbb043d authored over 2 years ago

add rainbow (#724)

* sync

* add rainbow

* add test for rainbow

8c758f56f033ac70a081c890a3e51905d2cabd53 authored over 2 years ago

Add a categorical Network (#625)

e1bfeada93ba8bbdd44a05d1b5a4ccae35901f1b authored over 2 years ago

Update Project.toml

0f00ba42a00aacbf7cd8a31ab6b6e3c4cf14c1ef authored over 2 years ago

Update compat in RLCore

9ee188a4d3f79c6392c639a04d9395d249d9274a authored over 2 years ago

added basic doc for `TDLearner` (#649)

* added basic doc for `TDLearner`

* Update src/ReinforcementLearningZoo/src/algorithms/tabula...

06aa63e06f255654e5ae967ec4737cafd4d77908 authored over 2 years ago

Update Project.toml

ae5060276a0c6f481faa2f14fffd913153a43458 authored over 2 years ago

CompatHelper: bump compat for "ReinforcementLearning" to "0.10" for package ReinforcementLearningExperiments

c3e67f928379ac1e4e3ce350d654d7ce7f5ed8f8 authored over 2 years ago

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

5ec49171dd3f90625ebc69c4253b8c33bec7c8fa authored over 2 years ago

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

14c38cdf53ea1f5a35bae2cb794557e861a46d9d authored over 2 years ago

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

23d58c206d246da90f909c260b34f1523e782f0e authored over 2 years ago

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

acace22adf22909c12c5226388144a255eaf2097 authored over 2 years ago

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

55a6dbc68b25bde1d596cfea10dc144af6307bf4 authored over 2 years ago

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

9f6676454fd14e9946d58eda22a6919b3d1f5f27 authored over 2 years ago

CompatHelper: bump compat for "ReinforcementLearningZoo" to "0.5"

59134724af05b3bb7c4e4264553af57b42afa768 authored over 2 years ago

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

34442fb5cd7fea6b70630116570d6c2024dfab38 authored over 2 years ago

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

bbbfd55ab759afe30f0773507c8f2ef03cfda317 authored over 2 years ago

Merge pull request #621 from HenriDeh/EpisodeResetCondition

Episode reset condition

89fe660566b450a6a560dc5d7e0f02d890685c78 authored over 2 years ago

Merge branch 'master' into EpisodeResetCondition

8732fb81a322ecbc6dae6b85be424abcc9e4af80 authored over 2 years ago

checkin Mainifest.toml (#711)

* checkin Mainifest.toml

* fix warning

* add missign dependency

b58c7c4e7c7ecb141df135023dd284cab487c6e0 authored over 2 years ago

spacing

7cac4a3d38cf52afead83f9e525cb73e40baae0d authored over 2 years ago

Merge branch 'EpisodeResetCondition' of https://github.com/HenriDeh/ReinforcementLearning.jl into EpisodeResetCondition

6e00c330e07f00ec7b7029ba309a0114169e9ded authored over 2 years ago

fix typo

ae26ac2206b218110d0c43522406059c53ffe66c authored over 2 years ago

Merge branch 'master' into EpisodeResetCondition

6e8575c475a2b03811c8531e3935487a41d6549d authored over 2 years ago

doc

3c531970c1374d9b89c7078d1176f7c028392655 authored over 2 years ago

move increment

937cae1c0a28c3c0c81d359b883091ebc62c0b56 authored over 2 years ago

spacing

a1687741e0ccd32e3d4484432778c29afb76be9a authored over 2 years ago

Merge branch 'master' into EpisodeResetCondition

b2924240b4d8b98c419cfeb39af1a5820c2cd67a authored over 2 years ago

add IQN (#710)

4acf579803a8f61beae9926dc6138c449ce1415b authored over 2 years ago

add REMDQN (#708)

83310a96475318af295b2f06808adcfdd8295cbf authored over 2 years ago

add QRDQN (#699)

* add QRDQN

fc74394b4552d09d50411fcb46d62c6b85ac3da9 authored over 2 years ago

add PrioritizedDQN (#698)

* add PrioritizedDQN

* add test for PrioritizedDQN

0d9032aa43a0a82ccfb4877cd0f5d40fd8cf742b authored over 2 years ago

fixed typo in customized environment docs (#697)

1d08e14e5239c6d04984556145ad67edef7c2e77 authored over 2 years ago

Merge pull request #695 from JuliaReinforcementLearning/HenriDeh-patch-2

Update the "how to implement a new algorithm"

77b33760e7d9554a43255cd6b480345d4045bd97 authored over 2 years ago

Update How_to_implement_a_new_algorithm.md

84941eecfd443fd805d78c0c05059f967ceb6a33 authored over 2 years ago

Update the "how to implement a new algorithm"

Given the recent changes, the tutorial was already outdated. I still need to update the extensio...

170a54d944d118c8f3ce832791625da868d84c6e authored over 2 years ago

Small improvements for TicTacToeEnv (#692)

* More explicit logging in TicTacToeEnv

* Fix type instability in TicTacToeEnv

9bfe4cf70eecf601d72c2de278f676cfc07ce1e8 authored over 2 years ago

enable OpenSpiel (#691)

* enable OpenSpiel

* passCI

c70f4f057202d6e02a39399458160002756b63ed authored over 2 years ago

Add `JuliaRL_DQN_CartPole` (#650)

* add back common networks

* add TwinNetwork

* sync

* add experiment JuliaRL_DQN_CartPole

d2bfd1f7b267be65a7b256ee967c6ce7be88aea8 authored over 2 years ago

Use Trajectories.jl instead (#632)

* sync

* finish agent.jl

* let's call it a day

* simplify code structure

* minimal c...

c67a604336923ee9120d75dee74456759860fcda authored over 2 years ago

just tag the latest code of [email protected] so that we can easily compare the performances in the future (#647)

2e1de3e5b6b8224f50b3d11bba7e1d2d72c6ef7c authored over 2 years ago

update node version (#645)

b0d9b58f8fef60739c157a99f0970b97b8966193 authored over 2 years ago

docs: add baedan as a contributor for code (#646)

* docs: update README.md [skip ci]

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

Co-authore...

467b81cd442f43a096caa4a6362368ac7e74ee76 authored over 2 years ago

created fallback implementation for legal_action_space_mask (#644)

* created fallback implementation for legal_action_space_mask

* fixed doc typo

cdfe41e9766fd67dfbd8d20674088dea44c26452 authored over 2 years ago

add a new notebook (#631)

* add a new notebook

* add link

51063056f32e64f68be3b7f32fe574a28ca4fbf4 authored over 2 years ago

Merge pull request #630 from JuliaReinforcementLearning/HenriDeh-patch-1

Update How_to_implement_a_new_algorithm.md

a4f4b2ca44fdaa23cb2dd5a4f5f88b3969313de7 authored over 2 years ago

Update How_to_implement_a_new_algorithm.md

39f6cd949ecaf7566b2ad896a16983cec70a4c73 authored over 2 years ago

Update How_to_implement_a_new_algorithm.md

0de216dee2b366aecbdf744eb8de795da0b04be7 authored over 2 years ago

docs: add tyleringebrand as a contributor for bug (#629)

* docs: update README.md [skip ci]

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

Co-authore...

d92531b9b219500e3b1caa6f455e44004dce06d2 authored over 2 years ago

fix #624 (#628)

* fix #624

* update readme

fae0614aa45f172dac781696c55804ec6b03d9e8 authored over 2 years ago

write doc (#627)

* write doc

* Update docs/src/How_to_implement_a_new_algorithm.md

* Update docs/src/How_to...

eaee54af84163659f07282e331bdb7ff343f7b37 authored over 2 years ago

more examples in docs

7c044ca899d70d63a37a307666a339090138bc4d authored almost 3 years ago

Merge branch 'EpisodeResetCondition' of https://github.com/HenriDeh/ReinforcementLearning.jl into EpisodeResetCondition

5a9efa2a46af3ed27a682dd72392a086382ac02c authored almost 3 years ago

fix typo

11299a028bd46b5f76c9b3bfabfa0048b4b97e65 authored almost 3 years ago

Merge branch 'master' into EpisodeResetCondition

5cbba6de80563fef82143cb7dfff5b1a192c13a3 authored almost 3 years ago

Merge pull request #622 from JuliaReinforcementLearning/HenriDeh-patch-1

cspell add Optimise

0a8b9a61ee44aae8db7a2da4bc4c111486125b3d authored almost 3 years ago

cspell add Optimise

fixes failing cspell check

d60204cb241990b0b3284cd032697fc4c2764150 authored almost 3 years ago

include

952c63da21dc1dd7ca072ca3acfc47b8ae04c770 authored almost 3 years ago

change to while cond

407b2e20701205644dcac28d2db94945be4f9970 authored almost 3 years ago

Doc strings

b682921220e8adb22500a6baa0b589cdcc7b8221 authored almost 3 years ago

make a doc page

32749f1a34901a9753a5ab7e1eb2b6c4cda81d84 authored almost 3 years ago

add a reset condition

1e051fe8f8fcbffc8a22d58d686640ce0c4733f4 authored almost 3 years ago

Ecosyste.ms: OpenCollective

github.com/JuliaReinforcementLearning/ReinforcementLearning.jl