ReinforcementLearning.jl Files

ReinforcementLearningEnvironments ReinforcementLearningEnvironments-v0.9.1

Diff since ReinforcementLearningEnvironments-v0.9.0

Merged pull requests: - Add missing Flux compat (#1059) (@jeremiahpslewis) - Fix docs / website build (#1064) (@jeremiahpslewis) - Correct Pendulum x-y coordinates (#1065) (@HenriDeh) - Make QBasedPolicy general for AbstractLearner s (#1069) (@dharux) - Fix hooks for multiplayer case (#1071) (@jeremiahpslewis) - Fix doc build errors (#1072) (@jeremiahpslewis) - bump rlcore version (#1073) (@jeremiahpslewis) - Make FluxApproximator work with QBasedPolicy (#1075) (@jeremiahpslewis) - Fix RLEnvs version (#1076) (@jeremiahpslewis)

Closed issues: - Next Release Plan (v0.11) (#614) - Package Stabilization Plan (#792) - test/runtests.jl empty (+ arch discussion) (#843) - policy(env) returns no legal action -inf initialized Q-table (#852) - Refactor CI into separate Workflows per package (and separate codecov projects per package) (#869) - Add deprecation warnings to non-refactored policies (#892) - Vectorized environments (#908) - Loading a Gym Environment (#912) - PPO with MaskedPPOTrajectory (#917) - Devmode is not working (#918) - TD3 Policy unable to handle environments with multidimensional action spaces (#951) - Spin off core packages (#960) - experiments failed (#982) - Breaking the tutorial by getting TotalRewardPerEpisode out of sync with the stopping condition in a run call (#1000) - Transfer Algorithms to RLFarm (#1028) - Update Buildkite script for gpu testing so it's sub package compatible (#1030) - Website: A practical introduction to RL: Does not introduce, source code is broken (#1036) - ElasticArraySARTSTraces does not record the trajectories of MountainCarEnv() correctly (#1067) - Algorithm implementations (#1070) - No method matching iterate ArrayProductDomain (#1074)