NTT123 / a0-jax
AlphaZero in JAX
☆68Updated 5 months ago
Related projects: ⓘ
- ☆46Updated last year
- fast + parallel AlphaZero in JAX☆80Updated 5 months ago
- Monte Carlo tree search in JAX, with functionality to continue search from a previous subtree☆14Updated 8 months ago
- An implementation of MuZero in JAX.☆52Updated last year
- CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRL☆102Updated 3 weeks ago
- Classic MCTS example with mctx☆15Updated last year
- Efficient baselines for autocurricula in JAX.☆165Updated 3 weeks ago
- A project that provides help for using DeepMind's mctx on gym-style environments.☆46Updated 5 months ago
- ☆59Updated last month
- MiniZero: An AlphaZero and MuZero Training Framework☆63Updated last month
- General Modules for JAX☆57Updated last month
- (Crafter + NetHack) in JAX. ICML 2024 Spotlight.☆189Updated 2 weeks ago
- ♟️ Vectorized RL game environments in JAX☆391Updated this week
- A fast, generalized, and modified implementation of Deepmind's distinguished AlphaZero in PyTorch.☆61Updated last year
- Standard interface for entity based reinforcement learning environments.☆35Updated 6 months ago
- ☆56Updated 3 weeks ago
- Pytorch Implementation of Stochastic MuZero for gym environment. This algorithm is capable of supporting a wide range of action and obser…☆50Updated 10 months ago
- A clean implementation of MuZero and AlphaZero following the AlphaZero General framework. Train and Pit both algorithms against each othe…☆153Updated 3 years ago
- Scaling scaling laws with board games.☆36Updated last year
- Simple single-file baselines for Q-Learning in pure-GPU setting☆87Updated last month
- Accelerated replay buffers in JAX☆39Updated 2 years ago
- cfrx is a collection of algorithms and tools for hardware-accelerated Counterfactual Regret Minimization (CFR) algorithms in Jax.☆27Updated last month
- Grandmaster-Level Chess Without Search☆52Updated 3 months ago
- JAX implementations of core Deep RL algorithms☆79Updated 2 years ago
- A simple implementation of MuZero algorithm for connect4 game☆93Updated 4 years ago
- Experimentation with Regularized Nash Dynamics on a GPU accelerated game☆37Updated last year
- ☆141Updated 2 weeks ago
- 🪐 The Sebulba architecture to scale reinforcement learning on Cloud TPUs in JAX☆46Updated 10 months ago
- Accelerated minigrid environments with JAX☆102Updated last month
- A clean implementation based on Expert Iterations for any game, inspired by alpha-zero-general☆40Updated last year