Yifan-Zhu

google-research

Google Research

manim

A community-maintained Python framework for creating mathematical animations.

modelscope

ModelScope: bring the notion of Model-as-a-Service to life.

awesome-mlss

🤖 Machine Learning Summer School deadlines

weread2notion

将微信读书划线同步到Notion

attention-learn-to-route

Attention based model for learning to solve different routing problems

diffuser

Code for the paper "Planning with Diffusion for Flexible Behavior Synthesis"

JaxMARL

Multi-Agent Reinforcement Learning with JAX

rl4co

A PyTorch library for all things Reinforcement Learning (RL) for Combinatorial Optimization (CO)

pgx

♟️ Vectorized RL game environments in JAX

Imitating-Human-Behaviour-w-Diffusion

Code for ICLR 2023 paper "Imitating Human Behaviour with Diffusion Models"

DeepACO

[NeurIPS 2023] DeepACO: Neural-enhanced Ant Systems for Combinatorial Optimization

endless-memory-gym

Challenging Memory-based Deep Reinforcement Learning Agents

learning-to-delegate

[NeurIPS 2021 Spotlight] Learning to Delegate for Large-scale Vehicle Routing

poppy

:hibiscus: Population-Based Reinforcement Learning for Combinatorial Optimization

MARVIN

Uber's Multi-Agent Routing Value Iteration Network

GFlowNet-CombOpt

PyTorch implementation for our NeurIPS 2023 spotlight paper "Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNets".

AdaptDiffuser

[ICML'2023] "AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners"

fast_irl

Contains implementation of the FILTER algorithm for exponentially faster inverse reinforcement learning.

user-in-the-box

UEyes-CHI2023

Code released for our CHI2023 paper "UEyes: Understanding Visual Saliency across User Interface Types"

icrl

Inverse Constrained Reinforcement Learning (ICML 2021)

HybridLearning

CAMA

Code for ICML2023 accepted paper: Complementary Attention for Multi-Agent Reinforcement Learning.

ICRL-benchmarks-public

spatially-aware-transformer

amortized-inference-hci

Rewriting-By-Generating

code for paper: 'Rewriting by Generating: Learn Heuristics for Large-scale Vehicle Routing Problems'

lori

Inferring Lexicographically-Ordered Rewards from Preferences

BICRL