#deep reinforcement learning

This repository is a resource for deep reinforcement learning, including both classic and advanced algorithms implemented in PyTorch. It provides code to aid understanding and experimentation, featuring models like DQN, PPO, and A3C. Actively maintained, the project plans to expand with new algorithms. It supports environments such as CartPole and BipedalWalker and includes installation guides, dependencies, and links to academic papers.

Explore the integration of deep reinforcement learning with the classic 1024 game, offering a perspective on human-AI collaboration and competition. This platform provides online gameplay and detailed reinforcement learning tutorials, including training MuZero and StochasticMuZero agents. Continuous project updates aim to introduce local model weights and innovative human-AI interaction algorithms. Discover more with DI-engine and LightZero for comprehensive insights into AI training.