lowrollr / mctx-az
Monte Carlo tree search in JAX, with functionality to continue search from a previous subtree
☆17Updated last year
Alternatives and similar repositories for mctx-az:
Users that are interested in mctx-az are comparing it to the libraries listed below
- A project that provides help for using DeepMind's mctx on gym-style environments.☆58Updated 4 months ago
- fast + parallel AlphaZero in JAX☆94Updated 3 months ago
- Classic MCTS example with mctx☆18Updated last year
- An implementation of MuZero in JAX.☆56Updated 2 years ago
- ☆74Updated 4 months ago
- Benchmarking RL for POMDPs in Pure JAX [Code for "Structured State Space Models for In-Context Reinforcement Learning" (NeurIPS 2023)]☆99Updated last year
- An Open-Ended Agentic Simulator☆45Updated 7 months ago
- ☆75Updated last week
- ☆50Updated last year
- Accelerated replay buffers in JAX☆41Updated 2 years ago
- General Modules for JAX☆64Updated last month
- Baselines for gymnax 🤖☆66Updated last year
- 🪐 The Sebulba architecture to scale reinforcement learning on Cloud TPUs in JAX☆57Updated last year
- Contains JAX implementation of algorithms for inverse reinforcement learning☆71Updated 7 months ago
- A number of agents (PPO, MuZero) with a Perceiver-based NN architecture that can be trained to achieve goals in nethack/minihack environm…☆40Updated 2 years ago
- Flax Implementation of DreamerV3 on Crafter☆14Updated last month
- ☆193Updated 3 months ago
- MiniZero: An AlphaZero and MuZero Training Framework☆85Updated last month
- JAX implementations of core Deep RL algorithms☆79Updated 2 years ago
- Vectorization techniques for fast population-based training.☆55Updated 2 years ago
- ⚡ Flashbax: Accelerated Replay Buffers in JAX☆229Updated this week
- AlphaZero in JAX☆77Updated 11 months ago
- JAX implementation of RL algorithms and vectorized environments☆42Updated last year
- Simple single-file baselines for Q-Learning in pure-GPU setting☆150Updated 2 weeks ago
- Accelerated minigrid environments with JAX☆132Updated 8 months ago
- CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRL☆109Updated 7 months ago
- Evaluating long-term memory of reinforcement learning algorithms☆141Updated last year
- Pytorch Implementation of Stochastic MuZero for gym environment. This algorithm is capable of supporting a wide range of action and obser…☆64Updated last year
- Single-file SAC-N implementation on jax with flax and equinox. 10x faster than pytorch☆50Updated last year
- Official Implementation of "Can Learned Optimization Make Reinforcement Learning Less Difficult"☆22Updated 4 months ago