meta-pytorch / LeanRLLinks
LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.
☆657Updated 3 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☆989Updated last year
- (Crafter + NetHack) in JAX. ICML 2024 Spotlight.☆357Updated 5 months ago
- Distributed Reinforcement Learning accelerated by Lightning Fabric☆409Updated last week
- 🏛️A research-friendly codebase for fast experimentation of single-agent reinforcement learning in JAX • End-to-End JAX RL☆375Updated last month
- RL Environments in JAX 🌍☆839Updated 6 months ago
- SBX: Stable Baselines Jax (SB3 + Jax) RL algorithms☆533Updated last week
- Multi-Agent Reinforcement Learning with JAX☆703Updated this week
- Hardware-Accelerated Reinforcement Learning Algorithms in pure Jax!☆250Updated last month
- Implementation of Q-Transformer, Scalable Offline Reinforcement Learning via Autoregressive Q-Functions, out of Google Deepmind☆404Updated 5 months ago
- Cost aware hyperparameter tuning algorithm☆176Updated last year
- A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities☆463Updated last week
- Reinforcement learning on general 2D physics environments in JAX. ICLR 2025 Oral.☆221Updated last month
- 🕹️ A diverse suite of scalable reinforcement learning environments in JAX☆785Updated last week
- Simple single-file baselines for Q-Learning in pure-GPU setting☆226Updated 2 weeks ago
- An API conversion tool for popular external reinforcement learning environments☆195Updated 2 weeks ago
- ⚡ Flashbax: Accelerated Replay Buffers in JAX☆265Updated 2 months ago
- Deep reinforcement learning without experience replay, target networks, or batch updates.☆274Updated 8 months ago
- ♟️ Vectorized RL game environments in JAX☆553Updated 9 months ago
- Streamlining reinforcement learning with RLOps. State-of-the-art RL algorithms and tools, with 10x faster training through evolutionary h…☆850Updated last week
- JAX (Flax) implementation of algorithms for Deep Reinforcement Learning with continuous action spaces.☆737Updated 3 years ago
- High throughput synchronous and asynchronous reinforcement learning☆958Updated 3 weeks ago
- Efficient baselines for autocurricula in JAX.☆201Updated last year
- Unified Implementations of Offline Reinforcement Learning Algorithms☆171Updated 2 months ago
- ☆243Updated last year
- Accelerated minigrid environments with JAX☆153Updated last month
- MR.Q is a general-purpose model-free reinforcement learning algorithm.☆128Updated 5 months ago
- [NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.☆858Updated last year
- Simplest and Cleanest DreamerV3 implementation out there☆121Updated 8 months ago
- Accelerated Quality-Diversity☆332Updated last month
- The Fastest Deep Reinforcement Learning Library☆907Updated 2 weeks ago