Releases: needle-mirror/com.unity.ml-agents
Releases · needle-mirror/com.unity.ml-agents
4.0.3
4.0.2
[4.0.2] - 2026-02-03
Minor Changes
com.unity.ml-agents (C#)
- Tests have been migrated to a companion package
com.unity.ml-agents.teststo conform with the recommandations and best practices of Unity (#6280)
4.0.1
[4.0.1] - 2025-12-04
Minor Changes
com.unity.ml-agents (C#)
2.0.2
[2.0.1] - 2021-10-13
Minor Changes
com.unity.ml-agents / com.unity.ml-agents.extensions (C#)
- Upgrade to 2.0.1
- Update gRPC native lib to universal for arm64 and x86_64. This change should enable ml-agents usage on mac M1 (#5283, #5519)
ml-agents / ml-agents-envs / gym-unity (Python)
- Set gym version in gym-unity to gym release 0.20.0(#5540)
- Harden user PII protection logic and extend TrainingAnalytics to expose detailed configuration parameters. (#5512)
- Added minimal analytics collection to LL-API (#5511)
Bug Fixes
com.unity.ml-agents / com.unity.ml-agents.extensions (C#)
- Fixed the bug where curriculum learning would crash because of the incorrect run_options parsing. (#5586)
4.0.0
[4.0.0] - 2025-08-15
Major Changes
com.unity.ml-agents (C#)
3.0.0
[3.0.0] - 2024-09-02
Major Changes
com.unity.ml-agents / com.unity.ml-agents.extensions (C#)
3.0.0-exp.1
[3.0.0-exp.1] - 2023-10-09
Major Changes
com.unity.ml-agents / com.unity.ml-agents.extensions (C#)
2.3.0-exp.3
[2.3.0-exp.3] - 2022-11-21
Major Changes
com.unity.ml-agents / com.unity.ml-agents.extensions (C#)
- The minimum supported Unity version was updated to 2021.3. (#)
ml-agents / ml-agents-envs
- Add your trainers to the package using Ml-Agents Custom Trainers plugin. (#)
- ML-Agents Custom Trainers plugin is an extensible plugin system to define new trainers based on the
High level trainer API, read more here.
- ML-Agents Custom Trainers plugin is an extensible plugin system to define new trainers based on the
- Refactored core modules to make ML-Agents internal classes more generalizable to various RL algorithms. (#)
- The minimum supported Python version for ML-agents has changed to 3.8.13. (#)
- The minimum supported version of PyTorch was changed to 1.8.0. (#)
- Add shared critic configurability for PPO. (#)
- We moved
UnityToGymWrapperandPettingZooAPI toml-agents-envspackage. All these environments will be
versioned underml-agents-envspackage in the future (#)
Minor Changes
com.unity.ml-agents / com.unity.ml-agents.extensions (C#)
- Added switch to RayPerceptionSensor to allow rays to be ordered left to right. (#26)
- Current alternating order is still the default but will be deprecated.
- Added suppport for enabling/disabling camera object attached to camera sensor in order to improve performance. (#31)
ml-agents / ml-agents-envs
- Renaming the path that shadows torch with "mlagents/trainers/torch_entities" and update respective imports (#)
Bug Fixes
com.unity.ml-agents / com.unity.ml-agents.extensions (C#)
ml-agents / ml-agents-envs
2.3.0-exp.2
[2.3.0-exp.2] - 2022-03-28
Major Changes
com.unity.ml-agents / com.unity.ml-agents.extensions (C#)
ml-agents / ml-agents-envs
- Refactored to support the new ML-Agents Pro package.
- The minimum supported Python version for ml-agents-envs was changed to 3.7.2 (#5)
- Added support for the PettingZoo multi-agent API (#6)
- Refactored
gym-unityinto theml-agents-envspackage (#6)
Minor Changes
com.unity.ml-agents / com.unity.ml-agents.extensions (C#)
- Upgrade barracuda dependency to 3.0.0 (#9)
ml-agents / ml-agents-envs
- Added the new unity_vec_env file to the ml-agents-envs module
- Extended support to python 3.9.10
Bug Fixes
com.unity.ml-agents / com.unity.ml-agents.extensions (C#)
ml-agents / ml-agents-envs
2.2.1-exp.1
[2.2.1-exp.1] - 2022-01-14
Major Changes
com.unity.ml-agents / com.unity.ml-agents.extensions (C#)
- The minimum supported Unity version was updated to 2020.3. (#5673)
- Added a new feature to replicate training areas dynamically during runtime. (#5568)
- Update Barracuda to 2.3.1-preview (#5591)