github Unity-Technologies/ml-agents release_15
ML-Agents Release 15

latest releases: release_21_docs, release_21, python-packages_1.0.0...
3 years ago

ML-Agents Release 15

Package Versions

NOTE: It is strongly recommended that you use packages from the same release together for the best experience.

Package Version (C#) v1.9.0 (C#) v0.3.0-preview
ml-agents (Python) v0.25.0
ml-agents-envs (Python) v0.25.0
gym-unity (Python) v0.25.0
Communicator (C#/Python) v1.5.0

Major Changes (C#)

ml-agents / ml-agents-envs / gym-unity (Python)

  • The MA-POCA trainer has been added. This is a new trainer that enables Agents to learn how to work together in groups. Configure poca as the trainer in the configuration YAML after instantiating a SimpleMultiAgentGroup to use this feature. (#5005)

Minor Changes / (C#)

  • Updated com.unity.barracuda to 1.3.2-preview. (#5084)
  • Added 3D Ball to the samples. (#5077)

ml-agents / ml-agents-envs / gym-unity (Python)

  • The encoding_size setting for RewardSignals has been deprecated. Please use network_settings instead. (#4982)
  • Sensor names are now passed through to (#5036)

Bug Fixes

ml-agents / ml-agents-envs / gym-unity (Python)

  • An issue that caused GAIL to fail for environments where agents can terminate episodes by self-sacrifice has been fixed. (#4971)
  • Made the error message when observations of different shapes are sent to the trainer clearer. (#5030)
  • An issue that prevented curriculums from incrementing with self-play has been fixed. (#5098)

Don't miss a new ml-agents release

NewReleases is sending notifications on new releases.