LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.
☆675Aug 22, 2025Updated 6 months ago
Alternatives and similar repositories for LeanRL
Users that are interested in LeanRL are comparing it to the libraries listed below
Sorting:
- Really Fast End-to-End Jax RL Implementations☆1,027Sep 9, 2024Updated last year
- High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, T…☆9,172Jul 8, 2025Updated 7 months ago
- SBX: Stable Baselines Jax (SB3 + Jax) RL algorithms☆562Updated this week
- Hardware-Accelerated Reinforcement Learning Algorithms in pure Jax!☆261Oct 31, 2025Updated 4 months ago
- 🏛️A research-friendly codebase for fast experimentation of single-agent reinforcement learning in JAX • End-to-End JAX RL☆395Feb 19, 2026Updated last week
- A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.☆3,315Updated this week
- C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.☆1,272Aug 12, 2024Updated last year
- RL Environments in JAX 🌍☆864May 30, 2025Updated 9 months ago
- Reinforcement learning on general 2D physics environments in JAX. ICLR 2025 Oral.☆230Jan 24, 2026Updated last month
- [NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.☆866Aug 12, 2024Updated last year
- Simple single-file baselines for Q-Learning in pure-GPU setting☆235Nov 24, 2025Updated 3 months ago
- 🕹️ A diverse suite of scalable reinforcement learning environments in JAX☆810Dec 1, 2025Updated 3 months ago
- ☆253Nov 19, 2024Updated last year
- Distributed Reinforcement Learning accelerated by Lightning Fabric☆423Feb 23, 2026Updated last week
- A framework for Reinforcement Learning research.☆247Feb 9, 2026Updated 3 weeks ago
- Partially Observable Process Gym☆212Jun 12, 2025Updated 8 months ago
- High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC…☆627Feb 10, 2024Updated 2 years ago
- (Crafter + NetHack) in JAX. ICML 2024 Spotlight.☆372Feb 10, 2026Updated 2 weeks ago
- CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRL☆122Aug 22, 2024Updated last year
- Benchmarked implementations of Offline RL Algorithms.☆77Mar 4, 2025Updated 11 months ago
- Modular Single-file Reinfocement Learning Algorithms Library☆38May 16, 2023Updated 2 years ago
- Simplifying reinforcement learning for complex game environments☆5,119Updated this week
- Official code release for "CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity"☆88Jun 4, 2024Updated last year
- A videogame made with PyGame turned into an Open AI Gym Learning Environment for Reinforcement Learning agents.☆15Jan 3, 2023Updated 3 years ago
- Multi-Agent Reinforcement Learning with JAX☆748Jan 14, 2026Updated last month
- The Fastest Deep Reinforcement Learning Library☆927Updated this week
- Standalone library of frequently-used wrappers for dm_env environments.☆18Jul 9, 2024Updated last year
- Efficient baselines for autocurricula in JAX.☆207Aug 24, 2024Updated last year
- Massively parallel rigidbody physics simulation on accelerator hardware.☆3,075Updated this week
- ⚡ Flashbax: Accelerated Replay Buffers in JAX☆273Sep 22, 2025Updated 5 months ago
- ☆1,407Dec 9, 2025Updated 2 months ago
- Clean single-file implementation of offline RL algorithms in JAX☆169Nov 24, 2025Updated 3 months ago
- Building blocks for productive research☆69Jan 12, 2026Updated last month
- Simple JAX Graphics Library.☆36Nov 3, 2024Updated last year
- ♟️ Vectorized RL game environments in JAX☆588Mar 6, 2025Updated 11 months ago
- JAX (Flax) implementation of algorithms for Deep Reinforcement Learning with continuous action spaces.☆752Oct 26, 2022Updated 3 years ago
- Parallel Q-Learning: Scaling Off-policy Reinforcement Learning under Massively Parallel Simulation☆76Aug 2, 2023Updated 2 years ago
- High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC…☆1,328Aug 3, 2023Updated 2 years ago
- Open-source codebase for EfficientZero, from "Mastering Atari Games with Limited Data" at NeurIPS 2021.☆925Dec 20, 2023Updated 2 years ago