pytorch-labs / LeanRLLinks
LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.
☆608Updated 9 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☆925Updated 10 months ago
- 🏛️A research-friendly codebase for fast experimentation of single-agent reinforcement learning in JAX • End-to-End JAX RL☆345Updated this week
- Distributed Reinforcement Learning accelerated by Lightning Fabric☆382Updated last week
- (Crafter + NetHack) in JAX. ICML 2024 Spotlight.☆330Updated 3 weeks ago
- Multi-Agent Reinforcement Learning with JAX☆609Updated 3 weeks ago
- RL Environments in JAX 🌍☆790Updated 2 months ago
- SBX: Stable Baselines Jax (SB3 + Jax) RL algorithms☆488Updated this week
- Hardware-Accelerated Reinforcement Learning Algorithms in pure Jax!☆230Updated 2 months ago
- 🕹️ A diverse suite of scalable reinforcement learning environments in JAX☆745Updated last month
- Reinforcement learning on general 2D physics environments in JAX. ICLR 2025 Oral.☆200Updated last week
- ⚡ Flashbax: Accelerated Replay Buffers in JAX☆242Updated this week
- Cost aware hyperparameter tuning algorithm☆166Updated last year
- Deep reinforcement learning without experience replay, target networks, or batch updates.☆257Updated 4 months ago
- Simple single-file baselines for Q-Learning in pure-GPU setting☆174Updated 4 months ago
- ♟️ Vectorized RL game environments in JAX☆510Updated 4 months ago
- A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities☆414Updated 2 weeks ago
- Streamlining reinforcement learning with RLOps. State-of-the-art RL algorithms and tools, with 10x faster training through evolutionary h…☆802Updated last week
- Implementation of Q-Transformer, Scalable Offline Reinforcement Learning via Autoregressive Q-Functions, out of Google Deepmind☆391Updated last month
- Efficient baselines for autocurricula in JAX.☆191Updated 11 months ago
- ☆235Updated 8 months ago
- Accelerated minigrid environments with JAX☆139Updated last week
- JAX (Flax) implementation of algorithms for Deep Reinforcement Learning with continuous action spaces.☆699Updated 2 years ago
- Accelerated Quality-Diversity☆313Updated last month
- An API conversion tool for popular external reinforcement learning environments☆173Updated 6 months ago
- [NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.☆836Updated 11 months ago
- High throughput synchronous and asynchronous reinforcement learning☆923Updated 2 months ago
- MR.Q is a general-purpose model-free reinforcement learning algorithm.☆106Updated last month
- Simplest and Cleanest DreamerV3 implementation out there☆80Updated 4 months ago
- Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning Framework on a GPU (JMLR 2022)☆487Updated 3 months ago
- Benchmarking the Spectrum of Agent Capabilities☆461Updated last year