lowrollr / turbozero_torchLinks
fast + parallel AlphaZero in PyTorch
☆12Updated last year
Alternatives and similar repositories for turbozero_torch
Users that are interested in turbozero_torch are comparing it to the libraries listed below
Sorting:
- fast + parallel AlphaZero in JAX☆96Updated 5 months ago
- Simple single-file baselines for Q-Learning in pure-GPU setting☆167Updated 2 months ago
- ☆80Updated 7 months ago
- Monte Carlo tree search in JAX, with functionality to continue search from a previous subtree☆20Updated last month
- Classic MCTS example with mctx☆18Updated 2 years ago
- General Modules for JAX☆66Updated 2 months ago
- CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRL☆113Updated 9 months ago
- ⚡ Flashbax: Accelerated Replay Buffers in JAX☆238Updated 2 months ago
- 🪐 The Sebulba architecture to scale reinforcement learning on Cloud TPUs in JAX☆57Updated last year
- ☆79Updated 2 months ago
- Hardware-Accelerated Reinforcement Learning Algorithms in pure Jax!☆219Updated last week
- Efficient baselines for autocurricula in JAX.☆187Updated 9 months ago
- AlphaZero in JAX☆77Updated last year
- MiniZero: An AlphaZero and MuZero Training Framework☆93Updated 3 months ago
- Accelerated minigrid environments with JAX☆138Updated 3 weeks ago
- Scaling scaling laws with board games.☆49Updated last year
- (Crafter + NetHack) in JAX. ICML 2024 Spotlight.☆314Updated last week
- Unified Implementations of Offline Reinforcement Learning Algorithms☆80Updated last month
- Clean single-file implementation of offline RL algorithms in JAX☆145Updated 5 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…☆41Updated 2 years ago
- Baselines for gymnax 🤖☆66Updated 2 years ago
- MR.Q is a general-purpose model-free reinforcement learning algorithm.☆102Updated last month
- ☆51Updated 2 years ago
- 🏛️A research-friendly codebase for fast experimentation of single-agent reinforcement learning in JAX • End-to-End JAX RL☆332Updated last week
- Efficient World Models with Context-Aware Tokenization. ICML 2024☆100Updated 8 months ago
- Experimentation with Regularized Nash Dynamics on a GPU accelerated game☆47Updated 2 years ago
- A project that provides help for using DeepMind's mctx on gym-style environments.☆60Updated 6 months ago
- An implementation of MuZero in JAX.☆56Updated 2 years ago
- Cost aware hyperparameter tuning algorithm☆154Updated 11 months ago
- Challenging Memory-based Deep Reinforcement Learning Agents☆99Updated 7 months ago