This is a PyTorch implementation of "Trust Region Policy Optimization (TRPO)".
This is code mostly ported from original implementation by John Schulman. In contrast to another implementation of TRPO in PyTorch, this implementation uses exact Hessian-vector product instead of finite differences approximation.
Contributions are very welcome. If you know how to make this code better, don't hesitate to send a pull request.
python main.py --env-name "Reacher-v1"
More or less similar to the original code. Coming soon.
- Plots.
- Collect data in multiple threads.