Reproducing MuJoCo benchmarks in a modern, commercial game /physics engine (Unity + PhysX).
Presented March 19th, 2018 at the AI Summit - Game Developer Conference 2018 - http://schedule.gdconf.com/session/beyond-bots-making-machine-learning-accessible-and-useful/856147
Legacy readme...
supports Unity ml-agents (instructions)
unity_oai_hopper.xml
1.5m steps
unity_dm_walker.xml
3m steps
unity_oai_hopper.xml
300k steps
2m steps
unity_dm_walker.xml
1m steps
3m steps
Note: to reproduce you'll need to figure out how to patch OpenAI baselines with Unity.
Ant - Random Ant - trained with ACKTR