meta-pytorch / LeanRLLinks
LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.
☆641Updated 2 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☆963Updated last year
- Distributed Reinforcement Learning accelerated by Lightning Fabric☆402Updated last week
- RL Environments in JAX 🌍☆819Updated 5 months ago
- (Crafter + NetHack) in JAX. ICML 2024 Spotlight.☆346Updated 3 months ago
- 🏛️A research-friendly codebase for fast experimentation of single-agent reinforcement learning in JAX • End-to-End JAX RL☆364Updated 3 weeks ago
- Hardware-Accelerated Reinforcement Learning Algorithms in pure Jax!☆243Updated last week
- SBX: Stable Baselines Jax (SB3 + Jax) RL algorithms☆516Updated 2 weeks ago
- Multi-Agent Reinforcement Learning with JAX☆669Updated this week
- 🕹️ A diverse suite of scalable reinforcement learning environments in JAX☆764Updated 2 weeks ago
- Deep reinforcement learning without experience replay, target networks, or batch updates.☆270Updated 7 months ago
- ⚡ Flashbax: Accelerated Replay Buffers in JAX☆256Updated last month
- Reinforcement learning on general 2D physics environments in JAX. ICLR 2025 Oral.☆215Updated 2 weeks ago
- A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities☆447Updated last week
- Implementation of Q-Transformer, Scalable Offline Reinforcement Learning via Autoregressive Q-Functions, out of Google Deepmind☆399Updated 4 months ago
- An API conversion tool for popular external reinforcement learning environments☆191Updated this week
- Cost aware hyperparameter tuning algorithm☆172Updated last year
- Efficient baselines for autocurricula in JAX.☆197Updated last year
- ☆240Updated 11 months ago
- Simple single-file baselines for Q-Learning in pure-GPU setting☆187Updated 7 months ago
- Streamlining reinforcement learning with RLOps. State-of-the-art RL algorithms and tools, with 10x faster training through evolutionary h…☆835Updated last week
- [NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.☆851Updated last year
- ♟️ Vectorized RL game environments in JAX☆535Updated 7 months ago
- Accelerated minigrid environments with JAX☆151Updated last week
- High throughput synchronous and asynchronous reinforcement learning☆946Updated 5 months ago
- JAX (Flax) implementation of algorithms for Deep Reinforcement Learning with continuous action spaces.☆724Updated 3 years ago
- MR.Q is a general-purpose model-free reinforcement learning algorithm.☆117Updated 4 months ago
- Accelerated Quality-Diversity☆324Updated this week
- Simplest and Cleanest DreamerV3 implementation out there☆104Updated 7 months ago
- [ICML 2024, Spotlight] EfficientZero V2: Mastering Discrete and Continuous Control with Limited Data☆95Updated last year
- Unified Implementations of Offline Reinforcement Learning Algorithms☆115Updated 2 weeks ago