meta-pytorch / LeanRLLinks
LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.
☆668Updated 5 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☆1,013Updated last year
- Distributed Reinforcement Learning accelerated by Lightning Fabric☆418Updated last week
- 🏛️A research-friendly codebase for fast experimentation of single-agent reinforcement learning in JAX • End-to-End JAX RL☆384Updated 2 months ago
- RL Environments in JAX 🌍☆848Updated 7 months ago
- (Crafter + NetHack) in JAX. ICML 2024 Spotlight.☆364Updated 6 months ago
- Multi-Agent Reinforcement Learning with JAX☆726Updated last week
- SBX: Stable Baselines Jax (SB3 + Jax) RL algorithms☆549Updated this week
- Hardware-Accelerated Reinforcement Learning Algorithms in pure Jax!☆257Updated 2 months ago
- Implementation of Q-Transformer, Scalable Offline Reinforcement Learning via Autoregressive Q-Functions, out of Google Deepmind☆406Updated 7 months ago
- 🕹️ A diverse suite of scalable reinforcement learning environments in JAX☆798Updated last month
- Deep reinforcement learning without experience replay, target networks, or batch updates.☆273Updated 10 months ago
- Simple single-file baselines for Q-Learning in pure-GPU setting☆232Updated 2 months ago
- Streamlining reinforcement learning with RLOps. State-of-the-art RL algorithms and tools, with 10x faster training through evolutionary h…☆866Updated this week
- Reinforcement learning on general 2D physics environments in JAX. ICLR 2025 Oral.☆226Updated last week
- A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities☆480Updated 2 weeks ago
- Cost aware hyperparameter tuning algorithm☆177Updated last year
- ☆249Updated last year
- ⚡ Flashbax: Accelerated Replay Buffers in JAX☆269Updated 4 months ago
- JAX (Flax) implementation of algorithms for Deep Reinforcement Learning with continuous action spaces.☆745Updated 3 years ago
- High throughput synchronous and asynchronous reinforcement learning☆970Updated 2 months ago
- ♟️ Vectorized RL game environments in JAX☆577Updated 10 months ago
- [NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.☆866Updated last year
- An API conversion tool for popular external reinforcement learning environments☆201Updated last month
- Efficient baselines for autocurricula in JAX.☆206Updated last year
- MR.Q is a general-purpose model-free reinforcement learning algorithm.☆131Updated 7 months ago
- Accelerated minigrid environments with JAX☆156Updated 3 months ago
- Simplest and Cleanest DreamerV3 implementation out there☆127Updated 10 months ago
- Unified Implementations of Offline Reinforcement Learning Algorithms☆195Updated last month
- Online Goal-Conditioned Reinforcement Learning in JAX. ICLR 2025 Spotlight.☆224Updated 2 months ago
- JAX-accelerated Meta-Reinforcement Learning Environments Inspired by XLand and MiniGrid 🏎️☆324Updated last month