kaesve / muzero
A clean implementation of MuZero and AlphaZero following the AlphaZero General framework. Train and Pit both algorithms against each other, and investigate reliability of learned MuZero MDP models.
☆157Updated 4 years ago
Alternatives and similar repositories for muzero:
Users that are interested in muzero are comparing it to the libraries listed below
- Pytorch Implementation of MuZero☆352Updated last year
- A structured implementation of MuZero☆204Updated 2 years ago
- ☆299Updated 4 months ago
- ♟️ Vectorized RL game environments in JAX☆473Updated 2 months ago
- Pytorch Implementation of Stochastic MuZero for gym environment. This algorithm is capable of supporting a wide range of action and obser…☆64Updated last year
- A simple implementation of MuZero algorithm for connect4 game☆97Updated 4 years ago
- Recurrent and multi-process PyTorch implementation of deep reinforcement Actor-Critic algorithms A2C and PPO☆200Updated 2 years ago
- An environment of the board game Go using OpenAI's Gym API☆172Updated 3 years ago
- Open-source codebase for EfficientZero, from "Mastering Atari Games with Limited Data" at NeurIPS 2021.☆894Updated last year
- A Python interface for reinforcement learning environments☆364Updated 2 years ago
- Experimentation with Regularized Nash Dynamics on a GPU accelerated game☆47Updated 2 years ago
- A fast, generalized, and modified implementation of Deepmind's distinguished AlphaZero in PyTorch.☆76Updated 4 months ago
- Accelerated Quality-Diversity☆290Updated last week
- AlphaZero in JAX☆77Updated last year
- Modular framework for Reinforcement Learning in python☆172Updated 2 years ago
- PyTorch implementation of DreamerV2 model-based RL algorithm☆217Updated 2 years ago
- Benchmarking the Spectrum of Agent Capabilities☆435Updated last year
- Dream to Control: Learning Behaviors by Latent Imagination, implemented in PyTorch.☆301Updated last year
- Vectorized interface for reinforcement learning environments☆140Updated 2 years ago
- Scalable implementation of DREAM - Deep RL for multi-agent imperfect information games☆117Updated 9 months ago
- A simple and highly efficient RTS-game-inspired environment for reinforcement learning (formerly Gym-MicroRTS)☆249Updated 10 months ago
- ⚡ Flashbax: Accelerated Replay Buffers in JAX☆234Updated last month
- fast + parallel AlphaZero in JAX☆96Updated 4 months ago
- A project that provides help for using DeepMind's mctx on gym-style environments.☆59Updated 5 months ago
- SBX: Stable Baselines Jax (SB3 + Jax) RL algorithms☆440Updated last week
- Code for the paper "Phasic Policy Gradient"☆261Updated 2 years ago
- ☆228Updated 5 months ago
- impact-driven-exploration☆131Updated last year
- Partially Observable Process Gym☆188Updated 10 months ago
- A grid-world game engine for game AI research☆240Updated last year