Alternatives and similar repositories for Craftax

Users that are interested in Craftax are comparing it to the libraries listed below

• instadeepai / flashbax
  ⚡ Flashbax: Accelerated Replay Buffers in JAX
  ☆238Updated 2 months ago
• EdanToledo / Stoix
  🏛️A research-friendly codebase for fast experimentation of single-agent reinforcement learning in JAX • End-to-End JAX RL
  ☆335Updated last week
• keraJLi / rejax
  Hardware-Accelerated Reinforcement Learning Algorithms in pure Jax!
  ☆226Updated 3 weeks ago
• mttga / purejaxql
  Simple single-file baselines for Q-Learning in pure-GPU setting
  ☆172Updated 3 months ago
• epignatelli / navix
  Accelerated minigrid environments with JAX
  ☆139Updated 2 weeks ago
• DramaCow / jaxued
  ☆81Updated 3 months ago
• FLAIROx / JaxMARL
  Multi-Agent Reinforcement Learning with JAX
  ☆595Updated 2 weeks ago
• Reytuag / transformerXL_PPO_JAX
  ☆80Updated 7 months ago
• facebookresearch / minimax
  Efficient baselines for autocurricula in JAX.
  ☆190Updated 10 months ago
• MichalBortkiewicz / JaxGCRL
  Goal-Conditioned Reinforcement Learning with JAX
  ☆169Updated last month
• vwxyzjn / cleanba
  CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRL
  ☆113Updated 10 months ago
• araffin / sbx
  SBX: Stable Baselines Jax (SB3 + Jax) RL algorithms
  ☆467Updated this week
• nissymori / JAX-CORL
  Clean single-file implementation of offline RL algorithms in JAX
  ☆146Updated 6 months ago
• adaptive-intelligent-robotics / QDax
  Accelerated Quality-Diversity
  ☆304Updated last week
• danijar / crafter
  Benchmarking the Spectrum of Agent Capabilities
  ☆454Updated last year
• openrlbenchmark / openrlbenchmark
  ☆232Updated 7 months ago
• kenjyoung / MinAtar
  ☆304Updated 6 months ago
• facebookresearch / MRQ
  MR.Q is a general-purpose model-free reinforcement learning algorithm.
  ☆104Updated 2 months ago
• Eclectic-Sheep / sheeprl
  Distributed Reinforcement Learning accelerated by Lightning Fabric
  ☆380Updated 2 weeks ago
• pytorch-labs / LeanRL
  LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.
  ☆597Updated 7 months ago
• RobertTLange / gymnax
  RL Environments in JAX 🌍
  ☆771Updated 3 weeks ago
• sotetsuk / pgx
  ♟️ Vectorized RL game environments in JAX
  ☆487Updated 3 months ago
• EmptyJackson / unifloral
  Unified Implementations of Offline Reinforcement Learning Algorithms
  ☆80Updated last month
• facebookresearch / dcd
  Implementations of robust Dual Curriculum Design (DCD) algorithms for unsupervised environment design.
  ☆130Updated 10 months ago
• proroklab / popgym
  Partially Observable Process Gym
  ☆193Updated last week
• jurgisp / memory-maze
  Evaluating long-term memory of reinforcement learning algorithms
  ☆143Updated 2 years ago
• lowrollr / turbozero
  fast + parallel AlphaZero in JAX
  ☆96Updated 6 months ago
• instadeepai / sebulba
  🪐 The Sebulba architecture to scale reinforcement learning on Cloud TPUs in JAX
  ☆57Updated last year
• kc-ml2 / SimpleDreamer
  A Simplified Pytorch Version of the Dreamer Algorithm
  ☆128Updated last year
• FLAIROx / Kinetix
  Reinforcement learning on general 2D physics environments in JAX. ICLR 2025 Oral.
  ☆188Updated 3 months ago