automl / arlbench
HPO and Architecture Benchmarking for RL: Dynamically, Reactive and Efficient
☆17Updated this week
Related projects ⓘ
Alternatives and complementary repositories for arlbench
- Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancy☆15Updated 3 weeks ago
- An Open-Ended Agentic Simulator☆28Updated 3 months ago
- POPGym Library in JAX☆11Updated 7 months ago
- Simple JAX Graphics Library.☆23Updated 3 weeks ago
- SkillHack: A Benchmark for Skill Transfer in Open-Ended Reinforcement Learning☆13Updated 2 years ago
- Efficient seed-parallel implementation of "Breaking the Replay Ratio Barrier"☆21Updated last year
- Fast and flexible multi-agent gridworld reinforcement learning environments.☆32Updated 3 weeks ago
- Accelerated replay buffers in JAX☆40Updated 2 years ago
- Single-file SAC-N implementation on jax with flax and equinox. 10x faster than pytorch☆46Updated last year
- Corax: Core RL in JAX☆35Updated 9 months ago
- Scalable Opponent Shaping Experiments in JAX☆21Updated 7 months ago
- ☆18Updated 4 months ago
- [ICLR 2024] Closing the Gap between TD Learning and Supervised Learning - A Generalisation Point of View.☆21Updated 7 months ago
- ☆34Updated last year
- ☆17Updated 5 months ago
- ☆63Updated 3 months ago
- Modular Single-file Reinfocement Learning Algorithms Library☆37Updated last year
- CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRL☆105Updated 3 months ago
- Vectorization techniques for fast population-based training.☆54Updated 2 years ago
- Jaxplorer is a Jax reinforcement learning (RL) framework for exploring new ideas.☆12Updated 4 months ago
- Challenging Memory-based Deep Reinforcement Learning Agents☆86Updated 3 weeks ago
- Conservative Q learning in Jax☆51Updated last year
- ☆36Updated last year
- Evaluating long-term memory of reinforcement learning algorithms☆133Updated last year
- Highly scalable 2D JAX physics engine.☆37Updated last week
- ☆42Updated last year
- Accompanying Code for "Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning", ICML 2023☆18Updated 10 months ago
- Official code release for "CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity"☆57Updated 5 months ago
- Learning diverse options through the Laplacian representation.☆22Updated 10 months ago
- ☆21Updated 2 years ago