automl / arlbench
HPO and Architecture Benchmarking for RL: Dynamically, Reactive and Efficient
☆14Updated last week
Related projects ⓘ
Alternatives and complementary repositories for arlbench
- An Open-Ended Agentic Simulator☆22Updated 3 months ago
- ☆34Updated last year
- ☆15Updated 6 months ago
- Conservative Q learning in Jax☆50Updated last year
- Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancy☆14Updated 2 weeks ago
- SkillHack: A Benchmark for Skill Transfer in Open-Ended Reinforcement Learning☆12Updated 2 years ago
- Simple JAX Graphics Library.☆13Updated last week
- Accelerated replay buffers in JAX☆39Updated 2 years ago
- [ICLR 2024] Closing the Gap between TD Learning and Supervised Learning - A Generalisation Point of View.☆21Updated 6 months ago
- ☆62Updated 2 months ago
- Modular Single-file Reinfocement Learning Algorithms Library☆37Updated last year
- Baselines for gymnax 🤖☆59Updated last year
- ☆28Updated 3 years ago
- ☆36Updated last year
- Efficient seed-parallel implementation of "Breaking the Replay Ratio Barrier"☆21Updated last year
- ☆20Updated 6 months ago
- Novelty MiniGrid--NovGrid--is an extension of MiniGrid environment that allows for the world properties and dynamics to change according …☆35Updated 5 months ago
- Jax2D is a highly scalable 2D physics engine written in JAX.☆29Updated this week
- Vectorization techniques for fast population-based training.☆54Updated 2 years ago
- Official code release for "CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity"☆57Updated 5 months ago
- Scalable Opponent Shaping Experiments in JAX☆21Updated 6 months ago
- ☆42Updated last year
- JAX reimplementation of the DeepMind paper "Genie: Generative Interactive Environments"☆33Updated 2 weeks ago
- Docker containers of baseline agents for the Crafter environment☆28Updated 2 years ago
- Reinforcement learning on general 2D physics environments in JAX☆10Updated this week
- Reinforcement Learning inside a 3D soccer simulation☆24Updated last month
- Jaxplorer is a Jax reinforcement learning (RL) framework for exploring new ideas.☆12Updated 3 months ago
- Single-file SAC-N implementation on jax with flax and equinox. 10x faster than pytorch☆46Updated last year
- Minimal Decision Transformer Implementation written in Jax (Flax).☆17Updated 2 years ago
- Change-Based Exploration Transfer☆36Updated 2 years ago