instadeepai / sebulbaLinks
πͺ The Sebulba architecture to scale reinforcement learning on Cloud TPUs in JAX
β58Updated last year
Alternatives and similar repositories for sebulba
Users that are interested in sebulba are comparing it to the libraries listed below
Sorting:
- β81Updated 9 months ago
- A collection of matrix games in JAXβ11Updated 8 months ago
- Accelerated replay buffers in JAXβ43Updated 2 years ago
- β82Updated 4 months ago
- β‘ Flashbax: Accelerated Replay Buffers in JAXβ242Updated this week
- Accelerated minigrid environments with JAXβ139Updated 2 weeks ago
- Simple single-file baselines for Q-Learning in pure-GPU settingβ176Updated 4 months ago
- CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRLβ114Updated 11 months ago
- Baselines for gymnax π€β68Updated 2 years ago
- General Modules for JAXβ67Updated 4 months ago
- Unified Implementations of Offline Reinforcement Learning Algorithmsβ88Updated 3 months ago
- Vectorization techniques for fast population-based training.β56Updated 2 years ago
- Jax-Baseline is a Reinforcement Learning implementation using JAX and Flax/Haiku libraries, mirroring the functionality of Stable-Baselinβ¦β55Updated this week
- Hardware-Accelerated Reinforcement Learning Algorithms in pure Jax!β230Updated 2 months ago
- Single-file SAC-N implementation on jax with flax and equinox. 10x faster than pytorchβ52Updated 2 years ago
- Official Implementation of "Can Learned Optimization Make Reinforcement Learning Less Difficult"β27Updated 3 months ago
- A project that provides help for using DeepMind's mctx on gym-style environments.β60Updated 8 months ago
- Benchmarking RL for POMDPs in Pure JAX [Code for "Structured State Space Models for In-Context Reinforcement Learning" (NeurIPS 2023)]β109Updated last year
- JAX implementations of core Deep RL algorithmsβ81Updated 3 years ago
- Simple JAX Graphics Library.β36Updated 9 months ago
- A collection of RL algorithms written in JAX.β102Updated 3 years ago
- Clean single-file implementation of offline RL algorithms in JAXβ150Updated 7 months ago
- Code and data for the paper "Bridging RL Theory and Practice with the Effective Horizon"β48Updated last year
- An Open-Ended Agentic Simulatorβ52Updated 11 months ago
- An implementation of MuZero in JAX.β56Updated 2 years ago
- Jax implementation of Proximal Policy Optimization (PPO) specifically tuned for Procgen, with benchmarked results and saved model weightsβ¦β58Updated 3 years ago
- Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancyβ18Updated 9 months ago
- β19Updated 2 months ago
- β47Updated 2 years ago
- Contains JAX implementation of algorithms for inverse reinforcement learningβ73Updated 11 months ago