jnesfield/TD7

Author's PyTorch implementation of TD7 for online and offline RL

For SALE: State-Action Representation Learning for Deep Reinforcement Learning

Official implementation of the TD7 algorithm.

Usage

Example online RL:

python main.py --env HalfCheetah-v4

Example offline RL:

python main.py --offline --env halfcheetah-medium-v2 

Software

Results were originally collected with:

• Gym 0.25.0
• MuJoCo 2.3.3
• Pytorch 2.0.0
• Python 3.9.13