github.com/JuliaReinforcementLearning/ReinforcementLearning.jl issues

Move UnicodePlots to extension

jeremiahpslewis opened this pull request 24 days ago

Bump RLFarm compat

jeremiahpslewis opened this pull request 25 days ago

Jpsl/update flux

jeremiahpslewis opened this pull request 25 days ago

CompatHelper: bump compat for Flux to 0.16 for package ReinforcementLearningCore, (keep existing compat)

github-actions[bot] opened this pull request 27 days ago

CompatHelper: bump compat for Flux to 0.15 for package ReinforcementLearningCore, (keep existing compat)

github-actions[bot] opened this pull request about 1 month ago

CompatHelper: bump compat for GPUArrays to 11 for package ReinforcementLearningCore, (keep existing compat)

github-actions[bot] opened this pull request 3 months ago

Fix and unit test for issue #1079

hespanha opened this pull request 4 months ago

Needless allocations in reward() and is_terminated() for

hespanha opened this issue 5 months ago

Wrong style for state report for TicTacToeEnv()

hespanha opened this issue 5 months ago

Does it allow defining an environment that has continuous action space? And how?

WuSiren opened this issue 6 months ago

Fix TagBot

jeremiahpslewis opened this pull request 8 months ago

Fix RLEnvs version

jeremiahpslewis opened this pull request 8 months ago

Make `FluxApproximator` work with `QBasedPolicy`

jeremiahpslewis opened this pull request 8 months ago

No method matching iterate ArrayProductDomain

ZdM87 opened this issue 8 months ago

bump rlcore version

jeremiahpslewis opened this pull request 9 months ago

Fix doc build errors

jeremiahpslewis opened this pull request 9 months ago

Fix hooks for multiplayer case

jeremiahpslewis opened this pull request 9 months ago

Algorithm implementations

johannes-fischer opened this issue 9 months ago

Make QBasedPolicy general for AbstractLearner s

dharux opened this pull request 9 months ago

It's not feasible to update the Q-based value agent in large steps for the RandomWalk1D() environment.

Van314159 opened this issue 9 months ago

ElasticArraySARTSTraces does not record the trajectories of `MountainCarEnv()` correctly

Van314159 opened this issue 9 months ago

Overspecific types in built-in policies and algorithms

dharux opened this issue 9 months ago

Correct Pendulum x-y coordinates

HenriDeh opened this pull request 9 months ago

Fix docs / website build

jeremiahpslewis opened this pull request 10 months ago

Update ReinforcementLearningAnIntroduction to be v0.11 compatible

jeremiahpslewis opened this issue 10 months ago

Add note about RLZoo deprecation

jeremiahpslewis opened this pull request 10 months ago

ReinforcementLearning.jl v0.12

jeremiahpslewis opened this issue 10 months ago

Update Website, fix broken references / issues

jeremiahpslewis opened this issue 10 months ago

Add missing Flux compat

jeremiahpslewis opened this pull request 10 months ago

Update Katex version, fix vulnerability

jeremiahpslewis opened this pull request 10 months ago

CompatHelper: bump compat for ReinforcementLearningTrajectories to 0.4 for package ReinforcementLearningCore, (keep existing compat)

github-actions[bot] opened this pull request 10 months ago

Update Docs for v0.11 release

jeremiahpslewis opened this pull request 10 months ago

Update versions

jeremiahpslewis opened this pull request 10 months ago

Fix abstract_learner for multiplayer games

jeremiahpslewis opened this pull request 10 months ago

Add TotalRewardPerEpisodeLastN hook

jeremiahpslewis opened this pull request 10 months ago

Epsilon Speedy Explorer

jeremiahpslewis opened this pull request 10 months ago

Update FluxModelApproximator references to FluxApproximator

jeremiahpslewis opened this pull request 10 months ago

Add SARS tdlearning back to lib

jeremiahpslewis opened this pull request 10 months ago

Fix naming consistency and add missing hook tests

jeremiahpslewis opened this pull request 10 months ago

Drop Functors and use Flux.@layer

jeremiahpslewis opened this pull request 10 months ago

Fix reset and stop conditions

jeremiahpslewis opened this pull request 10 months ago

Fix code coverage scope so it ignores test dir

jeremiahpslewis opened this pull request 10 months ago

Simplify Experiment code after dropping RLExperiment

jeremiahpslewis opened this pull request 10 months ago

Drop archived projects

jeremiahpslewis opened this pull request 10 months ago

Buildkite tweaks for monorepo

jeremiahpslewis opened this pull request 10 months ago

Swap RLZoo for RLFarm in CI, drop RLExperiments

jeremiahpslewis opened this pull request 10 months ago

Tabular Approximator fixes (pre v0.11 changes)

jeremiahpslewis opened this pull request 10 months ago

Review TabularApproximator

jeremiahpslewis opened this issue 10 months ago

Update docs script for new 'limited' RL.jl release

jeremiahpslewis opened this pull request 10 months ago

Website: How do implement a new algorithm is outdated

joelreymont opened this issue 10 months ago

Website: A practical introduction to RL: Does not introduce, source code is broken

joelreymont opened this issue 10 months ago

Drop devmode, prepare RL.jl v0.11 for release

jeremiahpslewis opened this pull request 10 months ago

Simple ReinforcementLearning example crashes

ropewe56 opened this issue 10 months ago

DRAFT: Add Tabular Learner

jeremiahpslewis opened this pull request 10 months ago

Fix RLZoo version

jeremiahpslewis opened this pull request 10 months ago

Bump RLZoo to v0.8

jeremiahpslewis opened this pull request 10 months ago

Update Buildkite script for gpu testing so it's sub package compatible

jeremiahpslewis opened this issue 10 months ago

GPU Code Migration Part 2.1

jeremiahpslewis opened this pull request 10 months ago

Transfer Algorithms to RLFarm

jeremiahpslewis opened this issue 10 months ago

Fix spell check CI errors

joelreymont opened this pull request 10 months ago

CI: Should spell check be dropped or fixed?

joelreymont opened this issue 10 months ago

Fix offline agent test

joelreymont opened this pull request 10 months ago

Tutorial OpenSpiel KuhnOpenNSFP fails

finmod opened this issue 10 months ago

GPU Code Migration Part 2

jeremiahpslewis opened this pull request 10 months ago

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

github-actions[bot] opened this pull request 10 months ago

Update TagBot.yml for subprojects

jeremiahpslewis opened this pull request 10 months ago

Initial GPUArray transition

jeremiahpslewis opened this pull request 10 months ago

Add Devcontainer, handle DomainSets 0.7

jeremiahpslewis opened this pull request 11 months ago

Fix RLCore version

jeremiahpslewis opened this pull request 11 months ago

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

github-actions[bot] opened this pull request 11 months ago

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

github-actions[bot] opened this pull request 11 months ago

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

github-actions[bot] opened this pull request 11 months ago

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

github-actions[bot] opened this pull request 11 months ago

Fix PPO per #1007

jeremiahpslewis opened this pull request 11 months ago

Bump RLCore, RLEnv

jeremiahpslewis opened this pull request 11 months ago

RL Env tests fail with latest OpenSpiel patches

joelreymont opened this issue 11 months ago

RL Core tests fail sporadically

joelreymont opened this issue 11 months ago

Update gym.jl

SimonHashtag opened this pull request 11 months ago

Make it compatible with Adapt 4 and Metal 1

joelreymont opened this pull request 11 months ago

GPU Compile error on PPO with MaskedPPOTrajectory

qwjyh opened this issue 12 months ago

Bump tj-actions/changed-files from 35 to 41 in /.github/workflows

dependabot[bot] opened this pull request about 1 year ago

CompatHelper: bump compat for GPUArrays to 10 for package ReinforcementLearningCore, (keep existing compat)

github-actions[bot] opened this pull request about 1 year ago

CompatHelper: bump compat for Adapt to 4 for package ReinforcementLearningCore, (keep existing compat)

github-actions[bot] opened this pull request about 1 year ago

Update CQL_SAC.jl

HenriDeh opened this pull request about 1 year ago

Fix CQL on gpu

HenriDeh opened this pull request about 1 year ago

TicTacToeEnv allows illegal moves

colintbowers opened this issue about 1 year ago

Breaking the tutorial by getting TotalRewardPerEpisode out of sync with the stopping condition in a `run` call

colintbowers opened this issue about 1 year ago

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

github-actions[bot] opened this pull request about 1 year ago

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

github-actions[bot] opened this pull request about 1 year ago

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

github-actions[bot] opened this pull request about 1 year ago

params() is no longer supported in Flux

halyusuf25 opened this issue about 1 year ago

Conservative Q-Learning

HenriDeh opened this pull request about 1 year ago

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

github-actions[bot] opened this pull request about 1 year ago

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

github-actions[bot] opened this pull request about 1 year ago

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

github-actions[bot] opened this pull request about 1 year ago

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

github-actions[bot] opened this pull request about 1 year ago

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

github-actions[bot] opened this pull request about 1 year ago

remove rlenv dep for tests

HenriDeh opened this pull request over 1 year ago

CompatHelper: bump compat for CUDA to 5 for package ReinforcementLearningZoo, (keep existing compat)

github-actions[bot] opened this pull request over 1 year ago

CompatHelper: bump compat for CUDA to 5 for package ReinforcementLearningCore, (keep existing compat)

github-actions[bot] opened this pull request over 1 year ago

Ecosyste.ms: OpenCollective

github.com/JuliaReinforcementLearning/ReinforcementLearning.jl