Unity-Technologies/ml-agents 0.5.0

ML-Agents Beta 0.5.0

on GitHub

Important

We have reorganized the project repository. Please see Migrating from v0.4 to v0.5 documentation for more information. Highlighted changes to repository structure include:

• The python folder has been renamed ml-agents. It now contains a python package called mlagents.
• The unity-environment folder, containing the Unity project, has been renamed UnitySDK.
• The protobuf definitions used for communication have been added to a new protobuf-definitions folder.
• Example curricula and the trainer configuration file have been moved to a new config sub-directory.

Environments

To learn more about new and improved environments, see our Example Environments page.

Improved

The following environments have been changes to use Multi Discrete Action:

• WallJump
• BananaCollector

The following environment has been modified to use Action Masking:

• GridWorld

New Features

• [Gym] New package gym-unity which provides gym interface to wrap UnityEnvironment. More information here.

• [Training] Can now run multiple concurent training sessions with the --num-runs=<n> command line option. (Training sessions are independent, and do not improve learning performance.)

• [Unity] Meta-Curriculum. Supports curriculum learning in multi-brain environments.

• [Unity] Action Masking for Discrete Control - It is now possible to mask invalid actions each step to limit the actions an agent can take.

• [Unity] Action Branches for Discrete Control - It is now possible to define discrete action spaces which contain multiple branches, each with its own space size.

Changes

• Can now visualize value estimates when using models trained with PPO from Unity with GetValueEstimate().
• It is now possible to specify which camera the Monitor displays to.
• Console summaries will now be displayed even when running inference mode from python.
• Minimum supported Unity version is now 2017.4.

Fixes & Performance Improvements

• Replaced some activation functions to swish.
• Visual Observations use PNG instead of JPEG to avoid compression losses.
• Improved python unit tests.
• Fix to enable multiple training sessions on single GPU.
• Curriculum lessons are now tracked correctly.

Known Issues

• Ending training early using CTL+C does not save the model on Windows.
• Sequentially opening and closing multiple instances of UnityEnvironment within a single process is not possible.

Acknowledgements

Thanks to everyone at Unity who contributed to v0.5.0, as well as: @sterling000, @bartlomiejwolk, @Sohojoe, @Phantomb.