- Implementing custom features to integrate with Unity's MLagents package.
- Custom SAC implementation allowing for experience to be sampled from buffer with probability proportional to loss from the critic network.
- Custom Energy Based (AFlow) implementation for comparison against RL approaches.
- Custom RL programming technique to use expert heuristics to inform the critic network.
forked from Unity-Technologies/ml-agents
-
Notifications
You must be signed in to change notification settings - Fork 0
The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.
rmarrcode/ml-agents
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published
Languages
- Python 100.0%