View on GitHub

marathon-envs

A set of high-dimensional continuous control environments for use with Unity ML-Agents Toolkit.

Marathon Man

This repository explores the application of deep reinforcement learning for physics-based animation. It contains a set of high-dimensional continuous control benchmarks using Unity’s native physics simulator, PhysX. The environments can be trained using Unity ML-Agents or any OpenAI Gym compatible algorithm. This project may be useful for:

The Unity project has two parts. Both can be find in UnitySDK > Assets:

MarathonEnvs

Example-current-status,

1. Getting started

If you have further questions, feel free to join our Discord server

2. Contributors

v4.0 was created by:

v3.0 was created by:

Note: This project is the result of contributions from members of the Unity community (see below) who actively maintain the repository. As such, the contents of this repository are not officially supported by Unity Technologies.

3. Open issues

Currently, our main challenge is that results still look like if they came with this department of silly walks effect, (something that obviously does not appear in the demos of the papers). It is annoying, and we absolutely need to solve it if we want to have something that can be used in practice.

Weird Walks

4. Publications

5. Licensing

All the project is under Apache License Version 2.0, January 2004 http://www.apache.org/licenses/LICENSE-2.0 , with the single exception of the motion data for the quadruped is adapted under the available under the terms of the Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) license, as stated in their README,

6. References

Document last updated: 11.05.2021