Lamperougeyxy

Synthetic-PandoraHearts-Jack

ai-deadlines

:alarm_clock: AI conference deadline countdowns

anonymous_github

Anonymous Github is a proxy server to support anonymous browsing of Github repositories for open-science code and data.

CDS

[NeurIPS 2021] CDS achieves remarkable success in challenging benchmarks SMAC and GRF by balancing sharing and diversity.

CityFlow

A Multi-Agent Reinforcement Learning Environment for Large Scale City Traffic Scenario

DOP

Codes accompanying the paper "DOP: Off-Policy Multi-Agent Decomposed Policy Gradients" (ICLR 2021, https://arxiv.org/abs/2007.12322)

facmac

FinRL

FinRL: Financial Reinforcement Learning. 🔥

gem

go-explore

Code for Go-Explore: a New Approach for Hard-Exploration Problems

gps

Guided Policy Search

handful-of-trials

Experiment code for "Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models"

Homophily-MARL

Code for "Learning Homophilic Incentives in Sequential Social Dilemmas"

LESSON

MADDPG-1

Pytorch implementation of the MARL algorithm, MADDPG, which correspondings to the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments".

mbpo

Code for the paper "When to Trust Your Model: Model-Based Policy Optimization"

MPE-Multiagent-RL-Algos

Simple verification experiments codes for multi-agent RL using OpenAI MPE environment

multi-agent-PPO-on-SMAC

Implementations of MAPPO and IPPO on SMAC, the multi-agent StarCraft environment.

multiagent-particle-envs

Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"

Offline-Pre-trained-Multi-Agent-Decision-Transformer

pymarl2

Fine-tuned MARL algorithms on SMAC (100% win rates on most scenarios)

PyTorch-VAE

A Collection of Variational Autoencoders (VAE) in PyTorch.

QPLEX

RODE

Codes accompanying the paper "RODE: Learning Roles to Decompose Multi-Agent Tasks (ICLR 2021, https://arxiv.org/abs/2010.01523). RODE is a scalable role-based multi-agent learning method which effectively discovers roles based on joint action space decomposition according to action effects, establishing a new state of the art on the StarCraft multi-agent benchmark.

smac_plus

An open source benchmark for Multi Agent Reinforcement Learning

smacv2

Synthetic-PandoraHearts

TRPO-in-MARL

visualboyadvance-m

The continuing development of the legendary VBA gameboy advance emulator.

wqmix

Code for Weighted QMIX