github.com/JuliaReinforcementLearning/ReinforcementLearning.jl commits

Add a reward normalizer (#609)

* Create rewardnormalizer.jl

* inlcude and export

* Fix NaN

* comment

* typo

* re...

05851601879fe402c0f246439692705c72463839 authored almost 3 years ago

docs: add jarbus as a contributor for bug (#607)

* docs: update README.md [skip ci]

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

Co-authore...

f082e9f59531aa749bea63444ee83b31d808ef72 authored almost 3 years ago

fix #605 (#606)

* fix #605

* update NEWs

* use latest Flux.jl

e90240c587ba22c68c01ae78b743f29a447b8314 authored almost 3 years ago

fix test logdetLorU with Float64 (#603)

* test logdetLorU with Float64

This stabilizes the test in two ways:
- generating Sigma thi...

fd96fe648044f5dc2a5dee53cfac64824de0fd54 authored almost 3 years ago

Rewrite initialization of `StackFrames` (#602)

* fix 551

* update news

57c82b831cfe21fe9122aaac2d1c110863131430 authored almost 3 years ago

Add CovGaussianNetwork to work with covariance (#597)

* custom normalizer and multi action sampling

* Complete docs on gaussian normalizer

* Upg...

1da09a9db56527d6854a4383ee3a2db1e22c86cb authored almost 3 years ago

docs: add harwiltz as a contributor for bug (#601)

* docs: update README.md [skip ci]

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

* docs: up...

77c2981e1d5104a47c1596e1b9cea396ff2b2bb9 authored almost 3 years ago

Fixing Gaussian Network gradient (#598)

* custom normalizer and multi action sampling

* Complete docs on gaussian normalizer

* Upg...

935f68b6cb378f9929a8d9914eb388e86213c86d authored almost 3 years ago

CompatHelper: bump compat for "ArrayInterface" to "5" for package ReinforcementLearningCore (#590)

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

8d802334f45ee4c37eeaac31be110dc6015f8c5b authored almost 3 years ago

CompatHelper: bump compat for "ArrayInterface" to "4" for package ReinforcementLearningCore (#574)

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

aee34ecb0e5ac52369addf9e23fb8ffeb8dc4d89 authored almost 3 years ago

Update README.md (#599)

beb91432acf4ce7374e4ee3915e0e24d9e802623 authored almost 3 years ago

docs: add bileamScheuvens as a contributor for doc (#594)

* docs: update README.md [skip ci]

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

Co-authore...

acb718052cbbab36889f83bc724cdb031fdaa415 authored almost 3 years ago

Fix 2 typos (#593)

then => than
appxorimator => approximator

0fd2ab566bf8724b450837cfa9b505671fe8b9e3 authored almost 3 years ago

Update README.md

1e61318704444c7f4adb8ef9bc6653ace45599da authored almost 3 years ago

docs: add HenriDeh as a contributor for code, doc (#587)

* docs: update README.md [skip ci]

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

Co-authore...

9532628847aa8ec4586de3f7b0b57b2dc958e759 authored almost 3 years ago

Bump RLCore

6504f6ff0e9e90735800f31351cb118c60a2b74c authored almost 3 years ago

Fixing and generalizing GaussianNetwork (#592)

* custom normalizer and multi action sampling

* Complete docs on gaussian normalizer

* Upg...

a90c4858878e7fe697e9875d47c19bb76724b3f8 authored almost 3 years ago

fix: documentation typo (#591)

a27ca4623448f014881b5619848282eb3a632f78 authored almost 3 years ago

Bump

ec195429989625fc810c5d57fd1eaf2eec6a287b authored almost 3 years ago

docs: add NPLawrence as a contributor for code (#589)

* docs: update README.md [skip ci]

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

Co-authore...

4b5dcdf89c8b6739287dfbaa5631322c65b40a99 authored almost 3 years ago

using act_limit parameter in target_actor (#588)

b7cebb7a0daeb803346ad2b9f83b85646726edd8 authored almost 3 years ago

Bump version

a37201ce62cbef08c6e299cd806b91c6c07f26e2 authored almost 3 years ago

Default qnetwork initializer (#586)

* complete and update docstring

* Add default target qnetwork initializer

43e15b7a2ce1ff0c2c22e07e579fa7df7c30e047 authored almost 3 years ago

CompatHelper: bump compat for "FillArrays" to "0.13" for package ReinforcementLearningCore (#583)

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

25127ac493aefa9ffe425b4292250c8e713e9da4 authored almost 3 years ago

Update EpsilonGreedyExplorer example (#577)

6fe6aa01208c325f8f990032621c18b61d574b37 authored about 3 years ago

Update NEWS.md

39b7bd9aa82502fe9f6cf323362d72765b499f84 authored about 3 years ago

bump version of RLCore and RLZoo (#576)

d992e99a0359ba44212797daf5cb66e32a3a68a1 authored about 3 years ago

fix #568 (#573)

7adaf4a23aaee405cecc1476dd26082cc05364d7 authored about 3 years ago

Build docs with [email protected]

fd70de1c9c592135d3c7f4e56cb0587b1ef10c40 authored about 3 years ago

docs: add blegat as a contributor for doc (#571)

* docs: update README.md [skip ci]

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

Co-authore...

77b2e379f400d67a056d76a97461a0e4702f966f authored about 3 years ago

Fix documentation for environments (#570)

b9d8120f76fc370a48444dd8c67561d88b5a7a14 authored about 3 years ago

Fix 566 (#567)

* make bc gpu compatable

* bump version

* fix #566

6db7366921e95f3e4eaf2003ef21c1f79413a0b8 authored about 3 years ago

Fix typo in ospp_final_term_report_210370741/index.md (#565)

auxillary -> auxiliary

bf12819fbf89f9eccd49a4b1eca6fd0c8c66bf7e authored about 3 years ago

Update ci.yml

9b957a7e72b67599b55a0e3322b4930d7036d01d authored about 3 years ago

Run CI with [email protected] only

Seems CxxWrap is not working on [email protected] yet.

0af1fc61fd26047f12f0f5161976fe32afbe21f6 authored about 3 years ago

Remove unneeded method (#564)

3274dc728e847aac76ec75321dacf3bfb3bb1e96 authored about 3 years ago

Fix/rand interval (#563)

* Fix dummy action for continuous action spaces

* Fixed rand of an interval

* dummy action...

8c0a317e35921c7a989597f87f570f58578fb1cf authored about 3 years ago

Fix dummy action for continuous action spaces (#562)

f04b2b648c5cc14c415a38968be66f1bea866be6 authored about 3 years ago

docs: add Mo8it as a contributor for code (#561)

* docs: update README.md [skip ci]

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

Co-authore...

3288867b7f7387c5d5d3782ec85f4481c4953e22 authored about 3 years ago

Fix warning about kwargs.data (#560)

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

cddc492330e0354aba2e03fea3fc95f4e0b331f7 authored about 3 years ago

Fix/rand dummy action (#559)

* No need for rand for a dummy action

* Order functions more in call order

18f72c141c081c2eaaae880f8f9eb324ed6d1b4b authored about 3 years ago

docs: add kir0ul as a contributor for doc (#556)

* docs: update README.md [skip ci]

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

Co-authore...

84a374ef261d9d6584ec45555ef37caa69c2c635 authored about 3 years ago

fix: typo (#555)

61256bcf1c493914d5003f22e126c997332c2c39 authored about 3 years ago

docs: add andreyzhitnikov as a contributor for bug (#554)

* docs: update README.md [skip ci]

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

Co-authore...

3f96f0a5aa75d1eeb30d2e99eb9ef5d6e0cce6bd authored about 3 years ago

make bc gpu compatable (#553)

* make bc gpu compatable

* bump version

2253f7cc35b3038598956a141e2563a35c1f5f45 authored about 3 years ago

Bugfix with cart pole env (#552)

* add compat

* minor bugfix with CartPoleEnv

* bump version

999759a102decfd0fd529ede9732687b6f98195f authored about 3 years ago

add compat (#550)

e5d2dc9a41cabfd912df9af88f6937cd71c63aaf authored about 3 years ago

Make experiments GPU compatible (#549)

* update links to RLIntro

* bugfix with GPU version of A2C/A2CGAE

* gpu version fix

* m...

f4cf555f50e0333254ab099f5a643a587ec532d7 authored about 3 years ago

update links to RLIntro (#548)

732ecfc2615010189d9c2d402c313351b2591caf authored about 3 years ago

Fix bug in cart pole float32 (#547)

* fix bug of CartPoleEnv with Float32

* bump version

4060d7d5d91b094f5f3bd3d2cf011c4ce22ba1aa authored about 3 years ago

Bump version (#545)

* bump version

* update NEWS.md

4a24aeba9aa5a7a1696762dfa3ca22af1937c6df authored about 3 years ago

docs: add dylan-asmar as a contributor for code (#544)

* docs: update README.md [skip ci]

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

Co-authore...

d6b3905c4650e3f9fd1219f8d81d585791fe3584 authored about 3 years ago

Added a continuous option for CartPoleEnv (#543)

* Added a continuous option for CartPoleEnv

Extended the traditional CartPoleEnv to have a co...

86fd1a87c8354a3a246ae1e4eb1a5d34d7de252c authored about 3 years ago

fix RLIntro#64 (#542)

* fix https://github.com/JuliaReinforcementLearning/ReinforcementLearningAnIntroduction.jl/issue...

29266f3523471e474e93e5c80db4bfd256776aad authored over 3 years ago

fix RLIntro#63 (#541)

* fix https://github.com/JuliaReinforcementLearning/ReinforcementLearningAnIntroduction.jl/issue...

c09f2b5288934eeddd7013e028da4868ac260270 authored over 3 years ago

Bump version (#540)

* bump version

* NEWS.md

6455214cb36a6a16ecc0efaa45b72f7e424a9f47 authored over 3 years ago

docs: add harwiltz as a contributor for code, doc (#539)

* docs: update README.md [skip ci]

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

Co-authore...

88e97ea415199202a9aa00e08c2dbe23895ea709 authored over 3 years ago

Improves plotting for classical control experiments (#537)

* Adds plotting for pendulum

* Fixes documentation and spell check errors, uses markdown stri...

bc4bd916fffa2e9b4e8c17d7880bfa1788c966ce authored over 3 years ago

Fix rldatasets (#538)

* fix #530

* update NEWS

* fix ci error on RLDatasets

84554931375a1ab61c2ced363e01aa1193fdf7ea authored over 3 years ago

Fix 530 (#536)

* fix #530

* update NEWS

057fd0826313cb8ba74d72b591eb21d95f28b35c authored over 3 years ago

Refine the doc and make minor changes of TabularApproximator (#532)

* update doc of TabularApproximator

* enforce table array dimension

* add doc for TabularVAppr...

a79a3455a7ca9e1834ff446329f29947437b0ba2 authored over 3 years ago

Revert unexpected change in PPO (#535)

* revert

* return vector instead

ba60397b1a0f59514f2cc7e4577f3172f9706492 authored over 3 years ago

Fix bug in MaskedPPOTrajectory (#533)

* fix ppo

* bump version

004e2970198b4c095066a536d7fe32fb82bd41d2 authored over 3 years ago

bugfix with ZeroTo (#534)

* bugfix with ZeroTo

* bump version

651e02325c48c95294187329a3a41cb52231f871 authored over 3 years ago

Update Project.toml

5a7e30b811cca8e890d284c79d4cfb801927e026 authored over 3 years ago

docs: add bhatiaabhinav as a contributor for bug, code (#529)

* docs: update README.md [skip ci]

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

Co-authore...

a86ae91116f0d52fb142ab18377ba05c38dc5b6a authored over 3 years ago

Fix: getindex function for ZeroTo now extends Base (#528)

954506c45aeee91e80684e4c7a465211bc42f0c8 authored over 3 years ago

Bump rlenvs (#526)

* bump version

* update compat

acf52e73d5dcac50ce25ca4fe4559d69f9b171fa authored over 3 years ago

Fix rlexps (#525)

* resove subpackage registration error

* update github action

0cfeb87c191a05a46750e756cd190e787de9d446 authored over 3 years ago

Update compat & version (#524)

* disable formatter

* update compat

a971df795e52c2a283f25392adb27f19fc200e7d authored over 3 years ago

close #493 (#523)

ff5ccf70667230c81c1ae2c7b73116a8d08a526e authored over 3 years ago

docs: add 3rdCore as a contributor for bug, code (#522)

* docs: update README.md [skip ci]

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

Co-authore...

dd6c972a47c4fade778224bc679aba749bc1c59d authored over 3 years ago

fixed findmax unconsistency (#521)

* fixed Base.findmax unconsistency

* Update src/ReinforcementLearningCore/src/utils/base.jl
...

c6c5053fcc3229e363b4090f406e5dc54b26365d authored over 3 years ago

Update reward wrappers to be more consistent (#519)

* rewardoverridden -> rewardtransformed

* minor updates

* Update src/ReinforcementLearning...

e2c46731fc9f7813fd932db9871772836639df92 authored over 3 years ago

Update report (#518)

* Update report

* Update headers

b00d9bdc908535d859724cac82d92e98da153523 authored over 3 years ago

OSPP Report for RLDatasets.jl (#516)

* OSPP Report for RLDatasets.jl

* Fix Spellings

* Fix spellcheck and make some modificatio...

dc8cc1e05e342b04cd755e250d21070d5be240cc authored over 3 years ago

WIP to implement FQE (#515)

* WIP to implement FQE

* Fix Cspell

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

e7aa706d2156ba3acbfe3c43787153a7ae199ff3 authored over 3 years ago

update report (#513)

* update report

* update cite links

4d96d1df09fdeef910ce71eda6e51284aee8ac86 authored over 3 years ago

Fix random net init in sac example (#514)

3851546ec2ce529a490bb5dacc1b6e0ddaaea941 authored over 3 years ago

update report (#512)

* update report

92fe40198b83f2a70de0cfb749d7ede613d1da99 authored over 3 years ago

docs: add johannes-fischer as a contributor for code (#511)

* docs: update README.md [skip ci]

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

Co-authore...

ec925edcd954ca3be6eef11a8abc45f22a37637b authored over 3 years ago

Fix dispatch for is_discrete_space (#510)

isa(A, Type{B}) is true if and only if A and B are the same object and that object is a type (re...

f6b3b09c08f3ed2b36737f5680d90b1e8cdfb7b7 authored over 3 years ago

cpu and gpu test (#509)

dbe7f26a60c5ceecbacdb855914342fd54605c7d authored over 3 years ago

Update ED algorithm and the report. (#508)

* add gpu support for ed algorithm

* update the experiment and the result

* update the rep...

0627db44d47443ce2af1dd31e5b990d44ef9526b authored over 3 years ago

update offline RL experiment (#507)

* update PLAS experiment

* update

* update experiment

* update

3ff3fb3cc7dda3250d27f17718488196ecd7cda0 authored over 3 years ago

update discrete BCQ (#502)

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

3fe15b5fb9d77f1b99d414221a70b7a8d2eb92c1 authored over 3 years ago

Play OpenSpiel envs with NFSP and try to add ED algorithm. (#496)

* minor updates for nfsp and BehaviorCloingPolicy

* update openspiel.jl and wrappers.jl

* play...

bf5c5756390378bb2a6ff8f36c73845c522bf66d authored over 3 years ago

update BCQ (#501)

* update BCQ

* update

f1837a93c4c061925d92167c3480a423007dae5c authored over 3 years ago

Add support for deep ope in RLDatasets.jl (#500)

* Add deep ope

Add deep ope d4rl models, fix documentation, readme etc.

Fix seed in GymEnv.

*...

1a00766e9df3edc19cd7377a595b4563261a0356 authored over 3 years ago

Update BEAR algorithm (#498)

* update BEAR

* update

3396e60fd5a4fd33dd58451ce4924c27797a7ed5 authored over 3 years ago

Merge pull request #499 from JuliaReinforcementLearning/albheim/randn_float32_fix

More efficient float32 randn

5e3f9f2b1cedd8e1fffbf7b6aaa90c5cb399feb2 authored over 3 years ago

replace ndims with end

615974766fc5244190122c33a2e43ea7e8ccdae3 authored over 3 years ago

More efficient float32 randn

67abeba3b9dc016d129dde58a79a404816e41b09 authored over 3 years ago

fix bug (#497)

38cbfb51e9270eca8d606fcc59e3f803d7cc82c9 authored over 3 years ago

Add dm datasets (#495)

* Add dm datasets

dm control suite, dm_locomotion_humanoid, dm_locomotion_rodent datasets.

* F...

9185c8548197dd4a6ef0cd7c84c3531c491e6447 authored over 3 years ago

update vae (#494)

* update vae

2bb67453c90498eaa659aab0a50767fe1c1ade7f authored over 3 years ago

add vmpo algorithm (#492)

* add vmpo algorithm

* add cspell words for vmpo algorithm

* Update src/ReinforcementLearn...

5633fdb6a3630a1cd1cf00d33044b0b15a1afc78 authored over 3 years ago

Fix gsutil for windows and fix docs (#491)

* Fix gsutil for windows and fix docs

* Delete d4rl_policies.json

* Delete d4rl_policy.jl
...

11a06af1f3a91715dff967bee6dc8e05f8414518 authored over 3 years ago

Update report. (#489)

* update the description about maddpg

* minor updates about relative experiments

* update ...

e07d4cea04ce23914560f7cb63e91e62dc4d7694 authored over 3 years ago

Update prob function of `QBasedPolicy.` (#488)

* update prob for QBasedPolicy

* fix the error in the report

4b595f33402fff3f9cf8bb9b30250304846bb866 authored over 3 years ago

Ecosyste.ms: OpenCollective

github.com/JuliaReinforcementLearning/ReinforcementLearning.jl