This a Unity project of multi-tanks scenes , which is used to train with MARL algorithms.

Safe and Robust Experience Sharing for Deterministic Policy Gradient Algorithms

Source code for our paper "Learning to Communicate with Strangers via Channel Randomisation Methods"

Team-based Multi-agent Reinforcement Learning

Using MADDPG for solving Multi Agent Based Unity Environment

Greenwave project website.

Accepted by AROB 2021. For letting agents in traffic simulation behave more like humans, we propose a unified mechanism for agents learn to decide various accelerations on deep reinforcement learning and generate a traffic flow behaving variously to simulate the real traffic flow.

Build and test DRL algorithms in different environments

Using Reinforcement Learning Multi-Agent version of DDPG (Deep Deterministic Policy Gradient) algorithm to teach 2 agents how to play tennis

Pytorch-based package for multi-agent reinforcement learning in an iterated prisonner dilemma setting

Blogsite for Interactive Multi-Agent Reinforcement Learning project under the Intelligence Research Group at Computer Society, IEEE NITK Student Branch

Projects completed while enrolling in Udacity's Deep Reinforcement Learning Nanodegree

PettingZoo ConnectFour and TicTacToe examples, configured with Rye as dependency manager

A Sample Efficient and Generalizable Multi-Agent Reinforcement Learning Framework for Motion Planning

Minimal frameworks for multi-agent reinforcement learning with deep neaural network.

This project is a computer simulation of a multi-agent extended prisoner’s dilemma using manipulation. The aim is to investigate if the outcome for all agents is better with or without the possibility of manipulation.

Collection of research resources informing a new design intelligence

Learnable MAPF. “Distributed Heuristic Multi-Agent Path Finding with Communication” (DHC) algorithm from ICRA 2021 is implemented and benchmarked in out-of-distribution (OOD) scenarios. A new robust training loop to handle communication failures is introduced.

Multi-Agent Reinforcement Learning