/deep_rl

Project for enabling easy and basic Reinforcement Learning by using PyTorch & OpenAI Gym. Currently contains an implementation of the Soft-Actor-Critic algorithm.

Primary LanguagePython

Implementation of Soft-Actor-Critic (SAC)

This repository consists of a basic framework that allows to easily load a Gym environment and optimize an agent using SAC. The SAC algorithm: Soft-Actor-Critic.

Installation

The code is written in python 3.10 and uses the following packages:

Usage

Single Experiments

Experiments with a set of hyperparameters can be run with the main.py script.

Hyperparameter Grid Search

Experiments to find the best hyperparameters can be run with the hpo.py script.

Evaluation

The evaluate.py script can be used to evaluate a trained agent.

Results

TODO

  • Make a version that uses PyTorch Lightning
  • With PyTorch Lightning, make use of Weights & Biases for logging
  • Add support for distributed training (Vertex AI)