StoneT2000 / robojax
A high-performance reinforcement learning library in jax specialized for robotic learning
☆22Updated last year
Alternatives and similar repositories for robojax:
Users that are interested in robojax are comparing it to the libraries listed below
- ☆35Updated 2 years ago
- Model-based reinforcement learning (generative simulator models and planning agents)☆15Updated 3 years ago
- Modular Single-file Reinfocement Learning Algorithms Library☆37Updated last year
- Source code for the paper "Policy Architectures for Compositional Generalization in Control"☆30Updated 2 years ago
- ☆22Updated 3 months ago
- POPGym Library in JAX☆11Updated 11 months ago
- a modular reinforcement learning library with JAX agents☆25Updated last month
- A modular implementation of PPO, and soon hopefully other algorithms.☆26Updated last year
- ☆23Updated 2 years ago
- Implementation of Diversity Is All You Need (DIAYN) on top of Stable Baselines 3.☆12Updated 2 years ago
- ☆43Updated 6 months ago
- Corax: Core RL in JAX☆37Updated last year
- ☆47Updated 2 years ago
- Code and data for the paper "Bridging RL Theory and Practice with the Effective Horizon"☆45Updated 9 months ago
- ☆16Updated 11 months ago
- ☆75Updated 2 weeks ago
- Official codebase for "The Generalization Gap in Offline Reinforcement Learning" accepted to ICLR 2024☆28Updated 7 months ago
- ☆23Updated 11 months ago
- ☆24Updated 9 months ago
- Accelerated replay buffers in JAX☆41Updated 2 years ago
- EARL: Environment for Autonomous Reinforcement Learning☆37Updated 2 years ago
- Code for "Possibility Before Utility: Learning And Using Hierarchical Affordances" (ICLR 2022)☆14Updated 3 years ago
- Contains JAX implementation of algorithms for inverse reinforcement learning☆71Updated 7 months ago
- Efficient seed-parallel implementation of "Breaking the Replay Ratio Barrier"☆22Updated last year
- [ICLR 22] Value Gradient weighted Model-Based Reinforcement Learning.☆24Updated last year
- Vectorization techniques for fast population-based training.☆55Updated 2 years ago
- ☆17Updated last year
- Highly scalable 2D JAX physics engine.☆53Updated 3 weeks ago
- Single-file truly minimal implementation of state-of-the-art reinforcement learning algorithms.☆22Updated 2 years ago
- Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancy☆17Updated 5 months ago