meta-pytorch / LeanRLLinks
LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.
☆665Updated 4 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☆1,006Updated last year
- Distributed Reinforcement Learning accelerated by Lightning Fabric☆414Updated last week
- RL Environments in JAX 🌍☆843Updated 7 months ago
- SBX: Stable Baselines Jax (SB3 + Jax) RL algorithms☆545Updated last week
- 🏛️A research-friendly codebase for fast experimentation of single-agent reinforcement learning in JAX • End-to-End JAX RL☆378Updated 2 months ago
- Multi-Agent Reinforcement Learning with JAX☆707Updated 2 weeks ago
- (Crafter + NetHack) in JAX. ICML 2024 Spotlight.☆361Updated 5 months ago
- Hardware-Accelerated Reinforcement Learning Algorithms in pure Jax!☆251Updated 2 months ago
- 🕹️ A diverse suite of scalable reinforcement learning environments in JAX☆789Updated last month
- A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities☆472Updated last month
- Cost aware hyperparameter tuning algorithm☆176Updated last year
- Simple single-file baselines for Q-Learning in pure-GPU setting☆229Updated last month
- Reinforcement learning on general 2D physics environments in JAX. ICLR 2025 Oral.☆226Updated last month
- ⚡ Flashbax: Accelerated Replay Buffers in JAX☆268Updated 3 months ago
- Deep reinforcement learning without experience replay, target networks, or batch updates.☆272Updated 9 months ago
- Streamlining reinforcement learning with RLOps. State-of-the-art RL algorithms and tools, with 10x faster training through evolutionary h…☆856Updated last week
- Implementation of Q-Transformer, Scalable Offline Reinforcement Learning via Autoregressive Q-Functions, out of Google Deepmind☆406Updated 6 months ago
- ☆246Updated last year
- ♟️ Vectorized RL game environments in JAX☆563Updated 9 months ago
- Accelerated minigrid environments with JAX☆154Updated 2 months ago
- Simplest and Cleanest DreamerV3 implementation out there☆124Updated 9 months ago
- Unified Implementations of Offline Reinforcement Learning Algorithms☆183Updated last week
- High throughput synchronous and asynchronous reinforcement learning☆964Updated last month
- JAX (Flax) implementation of algorithms for Deep Reinforcement Learning with continuous action spaces.☆740Updated 3 years ago
- An API conversion tool for popular external reinforcement learning environments☆197Updated 2 weeks ago
- Efficient baselines for autocurricula in JAX.☆205Updated last year
- [NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.☆863Updated last year
- MR.Q is a general-purpose model-free reinforcement learning algorithm.☆130Updated 6 months ago
- Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning Framework on a GPU (JMLR 2022)☆498Updated 8 months ago
- Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac L…☆951Updated this week