github.com/JuliaReinforcementLearning/ReinforcementLearningCore.jl commits

Update README.md

ae56611f6bea5d9cc0c4601a1f43f09fd4b549e9 authored over 3 years ago by Jun Tian <[email protected]>

wip (#231)

f732b23c6642abb7f7a264ddc350d73eb00829eb authored over 3 years ago by Jinrae Kim <[email protected]>

wip (#230)

efb5a26dbe0eb8e73fd7d39f93e5657d5ea53ef7 authored over 3 years ago by Jinrae Kim <[email protected]>

Make methods conform to documentation (#228)

c14ec876311408096a677f1b998e307cafff4dc4 authored almost 4 years ago by Albin Heimerson <[email protected]>

Bump Version

3bcca0171037f3e5036ecacaf89e36b208cc8822 authored almost 4 years ago by Jun Tian <[email protected]>

use findmax Compat (#227)

e17473d8603b10248cc344fc8b0469faa717035f authored almost 4 years ago by Jun Tian <[email protected]>

Add support of length and fetch! for CircularArraySLARTTrajectory (#225)

* Test length on CircularArraySLARTTrajectory

* Add support for CircularArraySLARTTrajectory ...

bb476720c5d787650fd382d121f00af1eb2d6dac authored almost 4 years ago by Ilan Coulon <[email protected]>

Bump version

b6f80f82350ff5856b9ee861aa0ce78b7f885664 authored almost 4 years ago by Jun Tian <[email protected]>

Fix SLART type (#224)

* Fix SLART type

* Add test case for SLART

* Fix order of CircularArraySLARTTrajectory arg...

706e5345196dcffdbd2004191efb89aded8b4d87 authored almost 4 years ago by Ilan Coulon <[email protected]>

Merge pull request #215 from JuliaReinforcementLearning/auto-juliaformatter-pr

Automatic JuliaFormatter.jl run

e2c5152dc8be58c77ae8c86d671444da8b5e98d3 authored almost 4 years ago by norci <[email protected]>

Format .jl files

f895b0ea55d1ed48d50458fd4e7cb130be13d200 authored almost 4 years ago by findmyway <[email protected]>

refactor NeuralNetworkApproximator with `@forward` (#221)

b6cd83a9c2701414da9fd6658a7fd9d412ddf892 authored almost 4 years ago by norci <[email protected]>

add a new stop condition (#220)

which sets the time badget of each experiment.

c70f865cd3afdc7e7179e00ea6cfa7fc0545a5ec authored almost 4 years ago by norci <[email protected]>

in _run, add hook for PRE_EXPERIMENT_STAGE & Post... (#219)

43a010d26d1aa23a7e52972af19c2aceb621d80f authored almost 4 years ago by norci <[email protected]>

Fix typo

cfbd6247ce80cb5dd30353277b06af564da3cc03 authored almost 4 years ago by Jun Tian <[email protected]>

Bump version

e578e1817a7a3bd45fa578ac9ed298d3f2bba5e7 authored almost 4 years ago by Jun Tian <[email protected]>

support general trajectory (#218)

ab894df57b9c3305edf8e68912ed55d583590fde authored almost 4 years ago by Jun Tian <[email protected]>

add cache to speed up sampling (#216)

0ef4bb4332eb69061d1f4393e8c74f493b2d3c5f authored almost 4 years ago by Jun Tian <[email protected]>

Simplify trajectories (#217)

* simplify trajectory

* add VectorSATrajectory

a5314fc00964df016880035e589b019ba6fe221c authored almost 4 years ago by Jun Tian <[email protected]>

In DoEveryNEpisode, added a keyword argument stage. (#214)

Then it can be used for PreEpisodeStage & PostEpisodeStage.

6aa3b6b8368e073a2489c43b195b7015fe22f07e authored almost 4 years ago by norci <[email protected]>

refactor StopAfterNoImprovement (#213)

513d57738757b2df9a4568ee1c0133e1dc178d53 authored almost 4 years ago by norci <[email protected]>

Merge pull request #210 from JuliaReinforcementLearning/auto-juliaformatter-pr

Automatic JuliaFormatter.jl run

7a1e841e7df0148171d939c82511edf67ad74581 authored almost 4 years ago by norci <[email protected]>

Format .jl files

0cae1d1612a4ca29d5b5a3ba7628ed534f8bda1f authored almost 4 years ago by findmyway <[email protected]>

minor fix with RandomStartPolicy (#212)

66d6791a7e40d9c5350f776d55413a7d81411340 authored almost 4 years ago by Jun Tian <[email protected]>

Update TagBot.yml

63f306d99a6db736a1755a5d1e26f2aa8e8822dc authored almost 4 years ago by Jun Tian <[email protected]>

Update Project.toml

678df93c0627c6bdd0d95fb07b01048e001ed07d authored almost 4 years ago by Jun Tian <[email protected]>

fix doc string to pass doc building (#211)

8bab4e94f308678755d8dd8250e91c06bbccb311 authored almost 4 years ago by Jun Tian <[email protected]>

Update README.md

6f63fc6f44dd1551ab4691c7de9542018115cee5 authored almost 4 years ago by Jun Tian <[email protected]>

Bump version

56696ad20ec9083ff2115cd821befdee9ac7015a authored almost 4 years ago by Jun Tian <[email protected]>

bugfix with TabularRandomPolicy (#209)

f7968e9102889c8e56383ab4491b3fc62ad0d719 authored almost 4 years ago by Jun Tian <[email protected]>

bugfix with TabularRandomPolicy (#208)

d949fd2de57dd59d18718e1bbb9acff6400f9703 authored almost 4 years ago by Jun Tian <[email protected]>

Support rlintro (#200)

Removed CumulativeReward.
Bugfix with MultiAgentHook
Add VectorSARTTrajectory
Bugfix with Mul...

58a93d80b077f7a98178b1ee9a4b820e78fafbbc authored almost 4 years ago by Jun Tian <[email protected]>

CompatHelper: bump compat for "Adapt" to "3.1" (#204)

* CompatHelper: bump compat for "Adapt" to "3.1"

* Update compat of Adapt

Co-authored-by: ...

cf43981fd4abbd2f7747d558f9d62a9498424aea authored almost 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

CompatHelper: bump compat for "Functors" to "0.2" (#207)

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

969b259a24f25e4ac394d0eed6073f46d7f55fe5 authored almost 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Merge pull request #203 from JuliaReinforcementLearning/compathelper/new_version/2021-01-07-00-19-04-399-867728912

CompatHelper: bump compat for "FillArrays" to "0.11"

ba0c4562dc182e54a2f26705eada3a3a14156bd3 authored almost 4 years ago by norci <[email protected]>

Merge pull request #201 from JuliaReinforcementLearning/auto-juliaformatter-pr

Automatic JuliaFormatter.jl run

30f7e51fb43717a95621f104702e4605ddb7bc39 authored almost 4 years ago by norci <[email protected]>

Merge pull request #206 from norci/bugfix

bugfix in StopAfterNoImprovement.

650dc2774bde6235a6e29d2d75a93e1905d9a186 authored almost 4 years ago by norci <[email protected]>

bugfix in StopAfterNoImprovement.

02f2f45f603d76f0ad686a2537749344c8246097 authored almost 4 years ago by norci <[email protected]>

CompatHelper: bump compat for "FillArrays" to "0.11"

4540cbf4e1c8d61bbabf71fe8b4495dd470e6cd4 authored about 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Format .jl files

9d5ab2aa7343cbd9fbf96e9a9099b8c647142360 authored about 4 years ago by findmyway <[email protected]>

Format .jl files (#198)

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

882d1025a5b6f84cbcfa6b758c2c44d9f86a5854 authored about 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Bump version

074d57c7f5cfcc715ed6107aece0148149c919f8 authored about 4 years ago by Jun Tian <[email protected]>

a more efficient version of QBasedPolicy (#199)

24fed7f9ac14e001c48f5ca3338cb3a58fead2cc authored about 4 years ago by Jun Tian <[email protected]>

Bump version

6f89a108ada5409d295f563a161ccaa1867661f7 authored about 4 years ago by Jun Tian <[email protected]>

CompatHelper: bump compat for "Zygote" to "0.6" (#192)

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

94ad3f91a47699aeabece660007e6f790d5ba7c5 authored about 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Add MultiAgent and NamedPolicy (#196)

* add MultiAgent

* rename to NamedPolicy

* dispatch nameof to inner policy

* add MultiA...

f01c35e72352141ebb3cc65eaec532a54e892106 authored about 4 years ago by Jun Tian <[email protected]>

Merge pull request #197 from JuliaReinforcementLearning/auto-juliaformatter-pr

Automatic JuliaFormatter.jl run

b801ca4ebd1fb4c2fef8f1b2e13820835232cee0 authored about 4 years ago by norci <[email protected]>

Format .jl files

6c493c3acefed36f42c7eef48cbf99298b17bddc authored about 4 years ago by findmyway <[email protected]>

decouple the behavior of PreActStage (#195)

fdece8212b16925763e3e17370f361bc1eaed741 authored about 4 years ago by Jun Tian <[email protected]>

added doc in agent.jl (#193)

* added doc in agent.jl

* Update src/policies/agents/agent.jl

Co-authored-by: Jun Tian <fi...

767d95eea5c5776673d85453311b8c4fe3333e28 authored about 4 years ago by norci <[email protected]>

Merge pull request #190 from JuliaReinforcementLearning/auto-juliaformatter-pr

Automatic JuliaFormatter.jl run

124ef3dff3519fb9e44f929a8d9f13370d7d03af authored about 4 years ago by norci <[email protected]>

Format .jl files

cef1840d7f6976de0d958bf888f74ce0038f325e authored about 4 years ago by findmyway <[email protected]>

Add default checks (#191)

* add default checks

* simplify condition

5665e1d48d53ed430bc099da2958dc8e0fe47643 authored about 4 years ago by Jun Tian <[email protected]>

add RandomStartPolicy & restrict QBasedPolicy to return index of action (#189)

0cc7c7e58542fee55e97a9ad328907ab92ff47b3 authored about 4 years ago by Jun Tian <[email protected]>

Update RLBase to the latest version (#188)

* fix RLBase imported functions

* rename functions in RLBase

* update dependency

135e691b5e8f4db8ed04b8474b7b0ac2ab62932f authored about 4 years ago by Jun Tian <[email protected]>

Merge pull request #184 from JuliaReinforcementLearning/compathelper/new_version/2020-12-10-00-04-20-410-3331559028

CompatHelper: bump compat for "JLD" to "0.11"

899b1bc85c76f8e6c84193b2d99a5fdc4f1c3cb3 authored about 4 years ago by norci <[email protected]>

Merge pull request #182 from JuliaReinforcementLearning/auto-juliaformatter-pr

Automatic JuliaFormatter.jl run

ade34483f4926e2aa54420b5f0258ce357229c91 authored about 4 years ago by norci <[email protected]>

Format .jl files

e74ea3f28f825137cd07fac08445de40939c0a86 authored about 4 years ago by findmyway <[email protected]>

updated format_pr. (#186)

upgrade create-pull-request from v2 to v3
fixes JuliaReinforcementLearning/ReinforcementLearnin...

10d165413c0f880b2894a46804b50cdba0fd5557 authored about 4 years ago by norci <[email protected]>

updated github workflows. (#185)

1. copied CompatHelper from https://github.com/JuliaRegistries/CompatHelper.jl#11-create-the-wor...

f596284a31033277f9e143d3fc3d5f367cc01b1f authored about 4 years ago by norci <[email protected]>

update StopAfterNoImprovement. (#177)

use a closure to get the measured value.

1973e5204986d0a22c529c0b9d91c63759751c75 authored about 4 years ago by norci <[email protected]>

CompatHelper: bump compat for "JLD" to "0.11"

5aaebf9726859e730de5849d346075e7f40a1c73 authored about 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Update Project.toml

a2ed045cf3f8b27bec052e539e6cf69f7b954114 authored about 4 years ago by Jun Tian <[email protected]>

Bugfix with prioritized trajectory (#183)

* bugfix with prioritized traj

* fix bound error when stack_size is not nothing

* add test cas...

80f81897268a321891bf5a7dec09e97989a3c295 authored about 4 years ago by Jun Tian <[email protected]>

CompatHelper: add new compat entry for "Functors" at version "0.1" (#180)

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

88bddfac01b3c6dd1e27875eb3ef8238b18fa4d2 authored about 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

add ElasticSARTTrajectory (#181)

200340630b13b19bc4811505d11e252ec24e1263 authored about 4 years ago by Jun Tian <[email protected]>

Format .jl files (#179)

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

c770e2819a460f6fdff60fc8db8a8c4ed068c282 authored about 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Reorganize code structure to support distributed reinforcement learning (#169)

* bugfixes with trajectory

* simplify trajectories

* clean up utils

* revisit extension...

8c293d40fa6f2074cb86aafa2c697cdc6eb2f51a authored about 4 years ago by Jun Tian <[email protected]>

removed dup code in run.jl. (#170)

a6a3c44f6c4e6e73098889661766063ae2b5cd5e authored about 4 years ago by norci <[email protected]>

Remove test with Julia nightly build

7df1b5ed34a186d59fcd1a4a7407022343741318 authored about 4 years ago by Jun Tian <[email protected]>

Format .jl files (#166)

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

72f4886deb84fd985d15c0fb436dd2aa487c7d25 authored about 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Update build status badge

b61ebf7c65ab63803915f7154b803945b81ac68e authored about 4 years ago by Jun Tian <[email protected]>

Update build badge

dc3043cc58ac31ad0b90904b2275c30b89584be9 authored about 4 years ago by Jun Tian <[email protected]>

Add GitHub Actions CI (#168)

* remove Travis CI

* add GitHub Actions CI

85aed1b7e5ad561c57e2c3ab15d0555754bd7c99 authored about 4 years ago by Sid-Bhatia-0 <[email protected]>

Bump version

add77c821bef9d709bf8eee0521e27c25bed9fec authored about 4 years ago by Jun Tian <[email protected]>

Automated commit made by MassInstallAction.jl (#164)

caf9b7de4c6bf0f9472cee5841a2041941adbd5d authored about 4 years ago by Jun Tian <[email protected]>

CompatHelper: bump compat for "CUDA" to "2.1" (#151)

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

b1f3bbe8d10dba84c0690149dd2abd66e6990ba8 authored about 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Updates related to DistributedRL (#153)

* add StaticPolicy

* sync

* sync local changes

* sync

12f230b432b6d1821d9e306f0cbcab0832b63733 authored about 4 years ago by Jun Tian <[email protected]>

fix minor typos (#152)

df518b60103277adfb0a49f30902b96dcc16b9c2 authored about 4 years ago by Sid-Bhatia-0 <[email protected]>

Minor edits to CircularArrayBuffer (#149)

* need not redefine nframes for CircularArrayBuffer

* change fieldname from length to nframes...

0edc357269b3a07d2af8985cc729b2710ac478eb authored about 4 years ago by Sid-Bhatia-0 <[email protected]>

CompatHelper: bump compat for "FillArrays" to "0.10" (#147)

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

8cb45fa983e43517bd22adc38e1a8a28c2c3e7b7 authored about 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Revert auto format related changes (#148)

fa2c96be6ad786179bfc27dbca02f8729cf90b26 authored about 4 years ago by Jun Tian <[email protected]>

Update format_pr.yml

6118b029f3c2634d2d17a7e13f6b8f601e07bfa1 authored about 4 years ago by Jun Tian <[email protected]>

Update format_pr.yml

fc1dc57b4eb9a094b0d036c79dd551cab990372a authored about 4 years ago by Jun Tian <[email protected]>

Bump Version

b6375afb19d6d7621c8d4a815471713e810a1b64 authored about 4 years ago by Jun Tian <[email protected]>

Format .jl files (#145)

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

9366653bc76909f2441b12030617b1fd25bf19f5 authored about 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Format .jl files (#141)

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

71d28600eca5a8db834913e36de0c58f0e925b67 authored about 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Replace reservoir array with reservoir trajectory (#144)

* replace reservoir array with reservoir trajectory

* fix tests

* set global seed

603ab2b77f62db71282f07e5564e288f7bbf0c13 authored about 4 years ago by Jun Tian <[email protected]>

Split the logic of `run` into two steps to allow injecting checkers (#143)

* split the logic of run into two steps

a9fcedc25d0c1e98a2ed671bfeed822b850bb14a authored about 4 years ago by Jun Tian <[email protected]>

minor fix (#142)

cf3c99140a8e5704ad0d1930a39516b64fe2b20c authored about 4 years ago by Jun Tian <[email protected]>

improve tabular learner (#140)

1c23c91ac8aa89ce95d7c01695685dc10ed2ef42 authored over 4 years ago by Jun Tian <[email protected]>

CompatHelper: bump compat for "Distributions" to "0.24" (#139)

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

3b9a72f091dd2b7f9dc1f67fa166f291d99fe040 authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Update Project.toml

664449240c0a7c6ce62b462c7ff2e2dd894fa949 authored over 4 years ago by Jun Tian <[email protected]>

Update Distributions.jl

9fdaecc0784b5ee56af0e017877e8e403cb31855 authored over 4 years ago by Jun Tian <[email protected]>

Bump version

4c52b9fd8645aaf6a9267437aad9c58668331e8b authored over 4 years ago by Jun Tian <[email protected]>

Format .jl files (#135)

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

2f7293270cc2da45a31d38e84a37069f67606b47 authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Add extensions for distributions (#136)

* temporary fix of Distributions

* show UnionAll correctly

836f5f1bb5b6bffa5f29fbc8bf61775df53647cf authored over 4 years ago by Jun Tian <[email protected]>

Add reservoir_array_buffer (#133)

* add reservoir_array_buffer

* bugfix with ReservoirArrayBuffer

* minor improvement

* m...

f6c5fc0e69e840346030c09abc3a47304f496a68 authored over 4 years ago by Jun Tian <[email protected]>

normlogpdf - workaround for GPU differentiability (#134)

* add GPU differentiable logpdf for normal distributions

* add tests on GPU

Co-authored-by...

38f9d37e0bf3542308e50aaa70a1a0b71dfa4876 authored over 4 years ago by Roman Bange <[email protected]>

CompatHelper: bump compat for "GPUArrays" to "6.0" (#132)

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

286e4a26f1851e9aea74acce75c009eb89c83c08 authored over 4 years ago by github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Ecosyste.ms: OpenCollective

github.com/JuliaReinforcementLearning/ReinforcementLearningCore.jl