FLAIROx / Kinetix
Reinforcement learning on general 2D physics environments in JAX
☆10Updated this week
Related projects ⓘ
Alternatives and complementary repositories for Kinetix
- Jax2D is a highly scalable 2D physics engine written in JAX.☆29Updated this week
- Simple JAX Graphics Library.☆13Updated last week
- An Open-Ended Agentic Simulator☆22Updated 3 months ago
- ☆16Updated 3 months ago
- ☆62Updated 2 months ago
- JAX reimplementation of the DeepMind paper "Genie: Generative Interactive Environments"☆33Updated 2 weeks ago
- Official code release for "CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity"☆57Updated 5 months ago
- ☆40Updated 4 months ago
- 🪐 The Sebulba architecture to scale reinforcement learning on Cloud TPUs in JAX☆47Updated last year
- Skeleton for scalable and flexible Jax RL implementations☆63Updated last year
- ☆87Updated this week
- Accompanying Code for "Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning", ICML 2023☆17Updated 10 months ago
- A collection of matrix games in JAX☆10Updated this week
- [ICLR 2024] Closing the Gap between TD Learning and Supervised Learning - A Generalisation Point of View.☆21Updated 6 months ago
- ☆64Updated last week
- ☆37Updated last year
- SkillHack: A Benchmark for Skill Transfer in Open-Ended Reinforcement Learning☆12Updated 2 years ago
- OGBench: Benchmarking Offline Goal-Conditioned RL☆75Updated 2 weeks ago
- ☆42Updated last year
- Learning diverse options through the Laplacian representation.☆22Updated 10 months ago
- Official Implementation of "Can Learned Optimization Make Reinforcement Learning Less Difficult"☆12Updated last week
- ☆53Updated 3 weeks ago
- HIQL: Offline Goal-Conditioned RL with Latent States as Actions (NeurIPS 2023)☆76Updated 11 months ago
- [ICML 2023] Pre-train world model-based agents with different unsupervised strategies, fine-tune the agent's components selectively, and …☆33Updated 8 months ago
- Contains JAX implementation of algorithms for inverse reinforcement learning☆63Updated 2 months ago
- Single-file SAC-N implementation on jax with flax and equinox. 10x faster than pytorch☆46Updated last year
- JAX implementation of RL algorithms and vectorized environments☆34Updated 10 months ago
- Conservative Q learning in Jax☆50Updated last year
- Simple single-file baselines for Q-Learning in pure-GPU setting☆94Updated 3 months ago
- Efficient seed-parallel implementation of "Breaking the Replay Ratio Barrier"☆21Updated last year