instadeepai / sebulba
🪐 The Sebulba architecture to scale reinforcement learning on Cloud TPUs in JAX
☆49Updated last year
Related projects ⓘ
Alternatives and complementary repositories for sebulba
- A collection of matrix games in JAX☆10Updated 2 weeks ago
- ☆65Updated 3 weeks ago
- Accelerated replay buffers in JAX☆40Updated 2 years ago
- General Modules for JAX☆59Updated 3 months ago
- Simple single-file baselines for Q-Learning in pure-GPU setting☆104Updated 3 months ago
- An Open-Ended Agentic Simulator☆28Updated 3 months ago
- ☆63Updated 3 months ago
- ☆17Updated 4 months ago
- Vectorization techniques for fast population-based training.☆54Updated 2 years ago
- ☆149Updated this week
- CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRL☆105Updated 3 months ago
- Conservative Q learning in Jax☆51Updated last year
- Single-file SAC-N implementation on jax with flax and equinox. 10x faster than pytorch☆46Updated last year
- ⚡ Flashbax: Accelerated Replay Buffers in JAX☆213Updated 3 weeks ago
- Benchmarking RL for POMDPs in Pure JAX [Code for "Structured State Space Models for In-Context Reinforcement Learning" (NeurIPS 2023)]☆89Updated 11 months ago
- A tool for aggregating and plotting MARL experiment data.☆62Updated 2 weeks ago
- JAX implementation of deep RL agents with resets from the paper "The Primacy Bias in Deep Reinforcement Learning"☆99Updated 2 years ago
- Simple JAX Graphics Library.☆23Updated 3 weeks ago
- Code and data for the paper "Bridging RL Theory and Practice with the Effective Horizon"☆42Updated 4 months ago
- A collection of RL algorithms written in JAX.☆95Updated 2 years ago
- Corax: Core RL in JAX☆35Updated 9 months ago
- JAX implementation of RL algorithms and vectorized environments☆35Updated 10 months ago
- JAX implementations of core Deep RL algorithms☆79Updated 2 years ago
- ☆42Updated last year
- Accompanying Code for "Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning", ICML 2023☆18Updated 10 months ago
- Baselines for gymnax 🤖☆60Updated last year
- Highly scalable 2D JAX physics engine.☆37Updated last week
- Benchmarking RL generalization in an interpretable way.☆133Updated 9 months ago
- Skeleton for scalable and flexible Jax RL implementations☆63Updated last year
- Goal-Conditioned Reinforcement Learning with JAX☆95Updated this week