A reinforcement learning framework with the primary purpose of learning and cleaning up personal scripts.
pip install git+https://github.com/brandon-rozek/rltorch
This is a dictionary that is shared around the different components. Contains hyperparameters and other configuration values.
This component needs to support the standard openai functions reset and step.
A network takes a PyTorch nn.Module, PyTorch optimizer, and configuration.
Takes in a network and provides methods to sync a copy of the original network.
Typtically takes in a network which it then uses to help make decisions on which actions to take.
For example, the ArgMaxSelector chooses the action that produces the highest entry in the output vector of the network.
Stores experiences during simulations of the environment. Useful for later training.
Takes in a network and performs some sort of training upon it.