zzmtsvv

MOSE

Multi-level Online Sequential Experts (MOSE) for online continual learning problem. (CVPR2024)

scattermoe

Triton-based implementation of Sparse Mixture of Experts.

Odysseus-Transformer

hindsight-experience-replay

This is the pytorch implementation of Hindsight Experience Replay (HER) - Experiment on all fetch robotic environments.

schedule_free

Schedule-Free Optimization in PyTorch

PufferLib

Simplifying reinforcement learning for complex game environments

rejax

mintext

Minimal but scalable implementation of large language models in JAX

euler-scheduler

My implementation Diffusers-like Scheduler for performing Euler Method on Conditional Flow Matching models

Elastic-DT

[NeurIPS 2023] Implementation of Elastic Decision Transformer

online-dt

Online Decision Transformer

CLAP

Contrastive Language-Audio Pretraining

Reinformer

Official code for ICML 2024 paper Reinformer: Max-Return Sequence Modeling for offline RL

JAX-CORL

Clean single-file implementation of offline RL algorithms in JAX

long-range-arena

Long Range Arena for Benchmarking Efficient Transformers

croc

Easily and securely send things from one computer to another :crocodile: :package:

DVL

A Dual-RL method DVL: Dual-V Learning for offline and online reinforcement learning

flash-linear-attention

Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton

LLMTest_NeedleInAHaystack

Doing simple retrieval from LLM models at various context lengths to measure accuracy

tdmpc

Code for "Temporal Difference Learning for Model Predictive Control"

deepmind-research

This repository contains implementations and illustrative code to accompany DeepMind publications

tensorneat

GPU-accelerated NeuroEvolution of Augmenting Topologies (NEAT)

ThunderKittens

Tile primitives for speedy kernels

pvp

Official release for the code used in paper: Learning from Active Human Involvement through Proxy Value Propagation (NeurIPS 2023 Spotlight)

pgeon

Mava

🦁 A research-friendly codebase for fast experimentation of multi-agent reinforcement learning in JAX

memory-maze

Evaluating long-term memory of reinforcement learning algorithms

s5-pytorch

Pytorch implementation of Simplified Structured State-Spaces for Sequence Modeling (S5)

Craftax_Baselines

flash-attention-jax

Implementation of Flash Attention in Jax