Expand description
Reinforcement learning should be fast, safe and easy to use.
rsrl provides generic constructs for reinforcement learning (RL)
experiments in an extensible framework with efficient implementations of
existing methods for rapid prototyping.
Re-exports§
pub extern crate rsrl_domains as domains;pub extern crate spaces;
Modules§
- control
- Control agents module.
- fa
- Function approximation and value function representation module.
- params
- policies
- Agent policies module.
- prediction
- Prediction agents module.
- traces
- Eligibility trace types.