Code for our paper: Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation

This is the official implementation of Multi-Agent PPO (MAPPO).

Implementation of "Embedding Graph Auto-Encoder for Graph Clustering", IEEE Transactions on Neural Networks and Learning Systems.

Jax Official Implementation of Paper: S Zhang*, Oswin So*, K Garg, C Fan: "GCBF+: A Neural Graph Control Barrier Function Framework for Distributed Safe Multi-Agent Control".

Code for the MADDPG algorithm from the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"

Implementation of Recovery RL: Safe Reinforcement Learning With Learned Recovery Zones.

Safe robot learning

Pytorch implementation of "Safe Exploration in Continuous Action Spaces" [Dalal et al.]

In this repo we use Turtlebot 3 along with ROS 2 and Gazebo to explore an unknown csv environment, navigate through it and create a map

PyTorch implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and ....

PPO, DDPG, SAC implementation on mujoco environment

ROS 2 labs at Centrale Nantes, with Baxter robot

Multi-Agent Constrained Policy Optimisation (MACPO; MAPPO-L).

Code for the RL method MATD3 described in the paper "Reducing Overestimation Bias in Multi-Agent Domains Using Double Centralized Critics"

Portable LyX, migrated over from code.google.com/p/lytex