instadeepai / sebulba
πͺ The Sebulba architecture to scale reinforcement learning on Cloud TPUs in JAX
β57Updated last year
Alternatives and similar repositories for sebulba:
Users that are interested in sebulba are comparing it to the libraries listed below
- β76Updated last month
- β75Updated 5 months ago
- General Modules for JAXβ64Updated 2 weeks ago
- Accelerated replay buffers in JAXβ41Updated 2 years ago
- A collection of matrix games in JAXβ10Updated 4 months ago
- Simple single-file baselines for Q-Learning in pure-GPU settingβ156Updated last month
- Baselines for gymnax π€β66Updated 2 years ago
- Vectorization techniques for fast population-based training.β55Updated 2 years ago
- β‘ Flashbax: Accelerated Replay Buffers in JAXβ233Updated 3 weeks ago
- β18Updated 2 months ago
- Code of the paper: Debiasing Meta-Gradient Reinforcement Learning by Learning the Outer Value Functionβ13Updated 2 years ago
- Official Implementation of "Can Learned Optimization Make Reinforcement Learning Less Difficult"β22Updated 5 months ago
- An implementation of MuZero in JAX.β56Updated 2 years ago
- JAX implementations of core Deep RL algorithmsβ79Updated 2 years ago
- Single-file SAC-N implementation on jax with flax and equinox. 10x faster than pytorchβ52Updated last year
- CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRLβ111Updated 8 months ago
- An Open-Ended Agentic Simulatorβ47Updated 8 months ago
- Benchmarking RL for POMDPs in Pure JAX [Code for "Structured State Space Models for In-Context Reinforcement Learning" (NeurIPS 2023)]β100Updated last year
- Jax implementation of Proximal Policy Optimization (PPO) specifically tuned for Procgen, with benchmarked results and saved model weightsβ¦β54Updated 2 years ago
- Hardware-Accelerated Reinforcement Learning Algorithms in pure Jax!β201Updated 3 weeks ago
- Learning diverse options through the Laplacian representation.β23Updated last year
- Accelerated minigrid environments with JAXβ134Updated 8 months ago
- Highly scalable 2D JAX physics engine.β54Updated last month
- β44Updated last year
- Corax: Core RL in JAXβ37Updated last year
- A collection of RL algorithms written in JAX.β97Updated 2 years ago
- A categorised list of Multi-Agent Reinforcemnt Learning (MARL) papersβ51Updated 2 years ago
- Simple JAX Graphics Library.β37Updated 5 months ago
- Jax-Baseline is a Reinforcement Learning implementation using JAX and Flax/Haiku libraries, mirroring the functionality of Stable-Baselinβ¦β48Updated this week
- Evaluating long-term memory of reinforcement learning algorithmsβ141Updated last year