FLAIROx / KinetixLinks
Reinforcement learning on general 2D physics environments in JAX. ICLR 2025 Oral.
☆213Updated this week
Alternatives and similar repositories for Kinetix
Users that are interested in Kinetix are comparing it to the libraries listed below
Sorting:
- Unified Implementations of Offline Reinforcement Learning Algorithms☆106Updated 5 months ago
- Hardware-Accelerated Reinforcement Learning Algorithms in pure Jax!☆236Updated 4 months ago
- Highly scalable 2D JAX physics engine.☆60Updated 6 months ago
- ☆83Updated 3 weeks ago
- Efficient baselines for autocurricula in JAX.☆197Updated last year
- Simple single-file baselines for Q-Learning in pure-GPU setting☆184Updated 6 months ago
- Clean single-file implementation of offline RL algorithms in JAX☆156Updated 9 months ago
- MR.Q is a general-purpose model-free reinforcement learning algorithm.☆112Updated 3 months ago
- Online Goal-Conditioned Reinforcement Learning in JAX. ICLR 2025 Spotlight.☆188Updated 4 months ago
- ☆41Updated last year
- An Open-Ended Agentic Simulator☆52Updated last year
- Contains JAX implementation of algorithms for inverse reinforcement learning☆72Updated last year
- Simplest and Cleanest DreamerV3 implementation out there☆93Updated 6 months ago
- Simple JAX Graphics Library.☆36Updated 11 months ago
- Jax/Flax Implementation of TD-MPC2☆66Updated last month
- off-policy RL on long sequences☆145Updated last month
- ☆108Updated 7 months ago
- ☆84Updated 11 months ago
- ⚡ Flashbax: Accelerated Replay Buffers in JAX☆252Updated 2 weeks ago
- Accelerated minigrid environments with JAX☆149Updated last month
- The official implementation of "Horizon Reduction Makes RL Scalable"☆139Updated 2 months ago
- Code for "SimbaV2: Hyperspherical Normalization for Scalable Deep Reinforcement Learning"☆66Updated 4 months ago
- JAX implementation of RL algorithms and vectorized environments☆49Updated last year
- ☆74Updated last year
- Baselines for gymnax 🤖☆71Updated 2 years ago
- A framework for Reinforcement Learning research.☆161Updated last month
- Official Implementation of "Can Learned Optimization Make Reinforcement Learning Less Difficult"☆28Updated 5 months ago
- A tool for recording RL trajectories.☆107Updated 2 months ago
- Benchmarking RL for POMDPs in Pure JAX [Code for "Structured State Space Models for In-Context Reinforcement Learning" (NeurIPS 2023)]☆110Updated last year
- (Crafter + NetHack) in JAX. ICML 2024 Spotlight.☆336Updated 2 months ago