4.1 Minor release

• Adds additional reset parameters for more fine-grained control of visual themes.
• Fixes issue in gym wrapper related to end of episode information.
• Fixes issue with environment not being responsive to some reset parameters.

• Unity project updated to 2019.4 LTS.
• ML-Agents package updated to 1.1.0 (Release 3).
• Gym wrapper now uses registry by default to auto-download binary.

• Updated Unity project to 2019.2.8.
• Updated ML-Agents plugin to v0.10.

• v3.0 Open Source release available here.
  • Added evaluation script for benchmarking, along with official benchmarking guidelines here.

• v2.2 Hotfix release.
  • Resolves issue with reset parameters sometimes not being updated during env.reset.
  • Resolves issue where agents could possibly skip levels.

v2.1 Hotfix release.

• Resolves issue with new seeds not being applied on env.reset.
• Resolves issue with underspecified observation space.

v2.0 Obstacle Tower Challenge Round 2 Release.

• Towers can now be generated with up to 100 floors.
• Additional visual themes, obstacles, enemy types, and floor difficulties added.
• Additional reset parameters added to customize generated towers. Go here for details on the parameters and their values.
• Various bugs fixed and performance improvements.

v1.3 Hotfix release.

• Resolves memory leak when running in Docker.
• Fixes issue where environment could freeze on certain higher floors.

• Adds timeout_wait parameter to extend python wait time for Unity environment handshake.
• Adds realtime_mode parameter to launch Unity environment from API at real-time speed and render to the window.
• Updates Windows and Linux binaries to address launching issues.
• Updated v1.2 binary includes fixes for agent collision detection issues.

v1.1 - Obstacle Tower Challenge Round 1 Release.

• Improved determinism between resets.
• Fixed bug in room template leading to un-beatable floors.
• Improved rendering & communication speed.
• Simplified python package dependencies.
• Added guide on training agents using Dopamine & GCP