Competitive Multi-Agent RL Simulation Using ROS2 and Gazebo

Показать описание

In this tutorial we will train two robots (agents) to play a simple game against each other.

ROS2: Humble

The project is here:

robot mania
robotics
reinforcement learning
deep learning
python
ROS

Рекомендации по теме

Комментарии

This project is very well made- please make more content with RL being applied to manipulators and other robot forms!

educateme

Thanks for the project overview and files, great work! Question: in the video you used CPU to train, do you know if its possible to use the GPU for Gazebo?

monkeypoohonyou

hi nice tutorial do you provide online paid tutorial related to ROS2 ?

SutanMSA

RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! (when checking argument for argument mat1 in method wrapper_CUDA_addmm)
terminate called without an active exception
[ros2run]: Aborted

valuetradings

Competitive Multi-Agent RL Simulation Using ROS2 and Gazebo

Competitive Multi-Agent RL Simulation Using ROS2 and Gazebo

Multi-Agent Hide and Seek

Introduction to Multi-Agent Reinforcement Learning

AI Olympics (multi-agent reinforcement learning)

Multi-Agent Competitive Reinforcement Learning

Demand Response Using Multi-Agent Reinforcement Learning (April 6, 2021)

Multi-agent learning & evaluation for open world games - Sam Devlin, Microsoft Research

Multiagent DeepMind: Competitive Mode

ICAPS 2021 The Flatland Challenge: Multi-Agent Reinforcement Learning on Trains

How Multi-Agent AI learn by continuously competing against themselves | Self Play

Fully Decentralized RL in Complex Multi-Agent Settings

Multi-Agent Reinforcement Learning for Cooperative and Competitive Autonomous Vehicles | IROS 2023

Reinforcement Learning based evade from rocket

Dynamic Multi-Team Racing: Competitive Driving on 1/10-th Scale Vehicles via Learning in Simulation

Multi-Agent Deep Reinforcement Learning

AlphaStar: Grandmaster level in StarCraft II using multi-agent reinforcement learning

Large-Scale, Multiagent, Reinforcement Learning Control

RAPID: Autonomous Multi-Agent Racing Using Constrained Potential Dynamic Games

The Multi-Agent Reinforcement Learning in Malmo Competition (@ CogX 2018)

CODE Multi-Agent RL: 20x Code + ReDel + AgentScope

CogX 2018 - Learning to Play: The Multi-Agent Reinforcement Learning in Malmö (MARLÖ) Competition

Simulation run for Deep Reinforcement Learning Competition 'DeepTraffic v2.0' by MIT.

Simulation #421 Todor Markov - Multi-agent Environments

Simulating Collaborative Robots in a Massive Multi-Agent Game Environment (SCRIMMAGE)