v0.3.1

ReinforcementLearningCore v0.3.1

Diff since v0.3.0

Closed issues:

• Why is there no AbstractStopCondition type ? (#74)

Merged pull requests:

• Several enhancements to fix errors in RLZoo (#71) (@findmyway)
• Quick name correction in a batch_explorer file (#72) (@felixchalumeau)

v0.3.0

ReinforcementLearningCore v0.3.0

Diff since v0.2.5

Closed issues:

• improve find_all_max (#46)
• Support trainmode! and testmode! (#50)
• Prefetch data from trajectory for learner (#63)

Merged pull requests:

• CompatHelper: bump compat for "StatsBase" to "0.33" (#44) (@github-actions[bot])
• Simplify APIs (#47) (@findmyway)
• add ActorCritic (#51) (@findmyway)
• Extend trainmode! and testmode! (#53) (@findmyway)
• Support loading/saving agent (#55) (@findmyway)
• Add preprocessors (#60) (@findmyway)
• CompatHelper: add new compat entry for "ImageTransformations" at version "0.8" (#61) (@github-actions[bot])
• Bugfix/enhancements for loading/saving agent (#64) (@findmyway)
• Add experiment (#66) (@findmyway)
• remove the default implementation (#68) (@findmyway)
• Pretty print description (#69) (@findmyway)

v0.2.5

ReinforcementLearningCore v0.2.5

Diff since v0.2.4

Merged pull requests:

• minor bugfix with CircularCompactSARTSATrajectory (#39) (@findmyway)
• CompatHelper: bump compat for "Distributions" to "0.23" (#41) (@github-actions[bot])
• Allow GPUArrays v3.1.0. (#45) (@aterenin)

v0.2.4

ReinforcementLearningCore v0.2.4

Diff since v0.2.3

Closed issues:

• Bug with the length of CircularTrajectory (#24)

Merged pull requests:

• move some functions in RLCore to keep dependency in RLBase concise (#29) (@findmyway)
• CompatHelper: bump compat for "CUDAapi" to "4.0" (#31) (@github-actions[bot])
• Keep pop! always return element (#32) (@findmyway)
• Added gae_returns (#33) (@sriram13k)
• CompatHelper: bump compat for "GPUArrays" to "3.0" (#36) (@github-actions[bot])
• extend BatchExplorer (#37) (@findmyway)

v0.2.3

ReinforcementLearningCore v0.2.3

Diff since v0.2.2

Merged pull requests:

• Remove type requirement from CircularArrayBuffer. (#26) (@aterenin)
• Dev actor critic (#27) (@findmyway)

v0.2.2

ReinforcementLearningCore v0.2.2

Diff since v0.2.1

Merged pull requests:

• add doc (#25) (@findmyway)

v0.2.1

ReinforcementLearningCore v0.2.1

Diff since v0.2.0

Merged pull requests:

• return INVALID_ACTION when legal_actions are empty inside RandomPolicy (#22) (@findmyway)
• Support DRL related algorithms (#23) (@findmyway)

v0.2.0

ReinforcementLearningCore v0.2.0

Diff since v0.1.0

Merged pull requests:

• Dev (#18) (@findmyway)
• Install TagBot as a GitHub Action (#19) (@JuliaTagBot)
• CompatHelper: add new compat entry for "MacroTools" at version "0.5" (#20) (@github-actions[bot])

v0.1.0

First release!