dodox/fancy_rl
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Why was that h3?

Browse Source
This commit is contained in:
Dominik Moritz Roth 2024-06-02 11:59:26 +02:00
parent 78d79cf705
commit dd6c6b6165
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -34,7 +34,7 @@ Fancy RL provides two main components:
2. **Additional Modules for TRPL**: Designed to integrate with torchrl's primitives-first approach, these modules are ideal for building custom algorithms with precise trust region projections. 2. **Additional Modules for TRPL**: Designed to integrate with torchrl's primitives-first approach, these modules are ideal for building custom algorithms with precise trust region projections.
### Background on Trust Region Policy Layers (TRPL) ## Background on Trust Region Policy Layers (TRPL)
Trust region methods are essential in reinforcement learning for ensuring robust policy updates. Traditional methods like TRPO and PPO use approximations, which can sometimes violate constraints or fail to find optimal solutions. To address these issues, TRPL provides differentiable neural network layers that enforce trust regions through closed-form projections for deep Gaussian policies. These layers formalize trust regions individually for each state and complement existing reinforcement learning algorithms. Trust region methods are essential in reinforcement learning for ensuring robust policy updates. Traditional methods like TRPO and PPO use approximations, which can sometimes violate constraints or fail to find optimal solutions. To address these issues, TRPL provides differentiable neural network layers that enforce trust regions through closed-form projections for deep Gaussian policies. These layers formalize trust regions individually for each state and complement existing reinforcement learning algorithms.