v0.7.4

ReinforcementLearningCore v0.7.4

Diff since v0.7.3

Merged pull requests:

• Add support of length and fetch! for CircularArraySLARTTrajectory (#225) (@ilancoulon)
• use findmax in Compat (#227) (@findmyway)

v0.7.3

ReinforcementLearningCore v0.7.3

Diff since v0.7.2

Merged pull requests:

• in _run, add hook for PRE_EXPERIMENT_STAGE & Post... (#219) (@norci)
• add a new stop condition (#220) (@norci)
• refactor NeuralNetworkApproximator with @forward (#221) (@norci)
• Fix SLART type (#224) (@ilancoulon)

v0.7.2

ReinforcementLearningCore v0.7.2

Diff since v0.7.1

Merged pull requests:

• minor fix with RandomStartPolicy (#212) (@findmyway)
• refactor StopAfterNoImprovement (#213) (@norci)
• In DoEveryNEpisode, added a keyword argument stage. (#214) (@norci)
• add cache to speed up sampling (#216) (@findmyway)
• Simplify trajectories (#217) (@findmyway)
• support general trajectory in BatchSampler (#218) (@findmyway)

v0.7.1

ReinforcementLearningCore v0.7.1

Diff since v0.7.0

Merged pull requests:

• Fix doc string to pass doc building (#211) (@findmyway)

v0.7.0

ReinforcementLearningCore v0.7.0

Diff since v0.6.3

Merged pull requests:

• Support rlintro (#200) (@findmyway)
• CompatHelper: bump compat for "FillArrays" to "0.11" (#203) (@github-actions[bot])
• CompatHelper: bump compat for "Adapt" to "3" (#204) (@github-actions[bot])
• bugfix in StopAfterNoImprovement. (#206) (@norci)
• CompatHelper: bump compat for "Functors" to "0.2" (#207) (@github-actions[bot])
• Bugfix with TabularRandomPolicy (#208) (@findmyway)
• bugfix with TabularRandomPolicy (#209) (@findmyway)

v0.6.3

ReinforcementLearningCore v0.6.3

Diff since v0.6.2

Merged pull requests:

• A more efficient version of QBasedPolicy (#199) (@findmyway)

v0.6.2

ReinforcementLearningCore v0.6.2

Diff since v0.6.1

Merged pull requests:

• Add default checks (#191) (@findmyway)
• CompatHelper: bump compat for "Zygote" to "0.6" (#192) (@github-actions[bot])
• added doc in agent.jl (#193) (@norci)
• Decouple the behavior of PreActStage (#195) (@findmyway)
• Add MultiAgent and NamedPolicy (#196) (@findmyway)

v0.6.1

ReinforcementLearningCore v0.6.1

Diff since v0.6.0

Merged pull requests:

• added StopAfterNoImprovement. (#177) (@norci)
• CompatHelper: bump compat for "JLD" to "0.11" (#184) (@github-actions[bot])
• updated github workflows. (#185) (@norci)
• updated format_pr. (#186) (@norci)
• Update RLBase to the latest version (#188) (@findmyway)
• Add RandomStartPolicy & restrict QBasedPolicy to return index of action (#189) (@findmyway)

v0.6.0

ReinforcementLearningCore v0.6.0

Diff since v0.5.1

Closed issues:

• Is it possible to have multiple progress meters for ComposedStopCondition? (#160)

Merged pull requests:

• Add GitHub Actions CI (#168) (@Sid-Bhatia-0)
• Reorganize code structure to support distributed reinforcement learning (#169) (@findmyway)
• removed dup code in run.jl. (#170) (@norci)
• CompatHelper: add new compat entry for "Functors" at version "0.1" (#180) (@github-actions[bot])
• More enhancements (#181) (@findmyway)
• Bugfix with prioritized trajectory (#183) (@findmyway)

v0.5.1

ReinforcementLearningCore v0.5.1

Diff since v0.5.0

Merged pull requests:

• CompatHelper: bump compat for "FillArrays" to "0.10" (#147) (@github-actions[bot])
• Revert auto format related changes (#148) (@findmyway)
• Minor edits to CircularArrayBuffer (#149) (@Sid-Bhatia-0)
• CompatHelper: bump compat for "CUDA" to "2.1" (#151) (@github-actions[bot])
• fix minor typos (#152) (@Sid-Bhatia-0)
• Updates related to DistributedRL (#153) (@findmyway)
• MassInstallAction: Install the CompatHelper workflow on this repository (#164) (@findmyway)