TRPO
University of California (UC) BerkeleyAtari
The TRPO model is a atari model from University of California (UC) Berkeley with 33500.0 parameters.
About TRPO
We describe an iterative procedure for optimizing policies, with guaranteed monotonic improvement. By making several approximations to the theoretically-justified procedure, we develop a practical algorithm, called Trust Region Policy Optimization (T
Details
- Provider
- University of California (UC) Berkeley
- Task
- Atari
- Parameters
- 33500.0
- Released
- 2015-02-19
- Open weights
- No