Multi Agent MuJoCo

Multi-agent MuJoCo research focuses on developing and evaluating reinforcement learning algorithms for controlling multiple agents within the MuJoCo physics simulator, aiming to achieve efficient and robust cooperative behavior. Current research emphasizes offline learning from pre-collected datasets, addressing challenges like distributional shift and sparse rewards through techniques such as stationary distribution regularization and hierarchical reinforcement learning with options frameworks. These advancements are significant for improving the safety, efficiency, and generalizability of multi-agent systems in robotics and other domains, particularly by enabling the development of more robust and adaptable control strategies.

Papers

November 6, 2024

CPEG: Leveraging Consistency Policy with Consensus Guidance for Multi-agent Exploration
Yuqian Fu, Yuanheng Zhu, Haoran Li, Zijie Zhao, Jiajun Chai, Dongbin Zhao
Strong Consistency Efficient Exploration Cooperative Agent Multi Agent MuJoCo Multi Agent Particle Multi Agent Exploration Consensus Formation

October 11, 2024

Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning
Xinran Li, Ling Pan, Jun Zhang
Reinforcement Learning Multi Agent Reinforcement Learning Multi Agent Challenge Parameter Sharing Multi Agent MuJoCo Multi Agent Particle Mask Learning

October 2, 2024

ComaDICE: Offline Cooperative Multi-Agent Reinforcement Learning with Stationary Distribution Shift Regularization
The Viet Bui, Thanh Hong Nguyen, Tien Mai
Multi Agent Reinforcement Learning Multi Agent Offline Reinforcement Learning Action Free Offline Offline Multi Agent Reinforcement Learning Multi Agent MuJoCo Agent Training

September 14, 2024

Learning to enhance multi-legged robot on rugged landscapes
Juntao He, Baxi Chong, Zhaochen Xu, Sehoon Ha, Daniel I. Goldman
LeArning Abstract Legged Locomotion Robotic Platform Robot Performance Multi Agent MuJoCo Multi Legged Robot

August 1, 2024

MuJoCo MPC for Humanoid Control: Evaluation on HumanoidBench
Moritz Meser, Aditya Bhatt, Boris Belousov, Jan Peters
Global Evaluation Robot Behavior Multi Agent MuJoCo Humanoid Control

July 21, 2024

Temporal Abstraction in Reinforcement Learning with Offline Data
Ranga Shaarad Ayyagari, Anurita Ghosh, Ambedkar Dukkipati
Reinforcement Learning Hierarchical Reinforcement Learning Offline Data Multi Agent MuJoCo Standard Reinforcement Learning Temporal Abstraction

May 14, 2024

Zero-Shot Transfer of Neural ODEs
Tyler Ingebrand, Adam J. Thorpe, Ufuk Topcu
Autonomous System Formality Transfer Model Predictive Control Neural ODE Multi Agent MuJoCo

April 23, 2024

Closed Loop Interactive Embodied Reasoning for Robot Manipulation
Michal Nazarczuk, Jan Kristof Behrens, Karla Stepanova, Matej Hoffmann, Krystian Mikolajczyk
Multi Step Reasoning Robot Manipulation Robot Action Multi Agent MuJoCo Real World Manipulation Task Embodied Reasoning

March 11, 2024

DeepSafeMPC: Deep Learning-Based Model Predictive Control for Safe Multi-Agent Reinforcement Learning
Xuefeng Wang, Henglin Pu, Hyung Jun Kim, Husheng Li
Multi Agent Reinforcement Learning Predictive Control Multi Agent MuJoCo Safe Multi Agent Reinforcement Learning

December 21, 2023

Open-Source Reinforcement Learning Environments Implemented in MuJoCo with Franka Manipulator
Zichun Xu, Yuntao Li, Xiaohang Yang, Zhiyuan Zhao, Lei Zhuang, Jingdong Zhao
Serial Manipulator Multi Agent MuJoCo Multi Goal Reinforcement Learning Open Source Reinforcement Learning

December 5, 2023

Similarity-based Knowledge Transfer for Cross-Domain Reinforcement Learning
Sergio A. Serrano, Jose Martinez-Carranza, L. Enrique Sucar
Knowledge Transfer Learning Agent Alignment Loss Multi Agent MuJoCo Cross Domain Reinforcement Learning

October 8, 2023

FP3O: Enabling Proximal Policy Optimization in Multi-Agent Cooperation with Parameter-Sharing Versatility
Lang Feng, Dong Xing, Junru Zhang, Gang Pan
Multi Agent Reinforcement Learning Proximal Policy Optimization Parameter Sharing Multi Agent Cooperation Multi Agent MuJoCo PPO Algorithm

August 13, 2023

Heterogeneous Multi-Agent Reinforcement Learning via Mirror Descent Policy Optimization
Mohammad Mehdi Nasiri, Mansoor Rezghi
Cooperative Multi Agent Reinforcement Learning Heterogeneous Agent Multi Agent MuJoCo Heterogeneous Multi Agent Reinforcement Learning Policy Mirror

July 21, 2023

Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization
Xiangsen Wang, Haoran Xu, Yinan Zheng, Xianyuan Zhan
Multi Agent Reinforcement Learning Multi Agent Offline Reinforcement Learning Implicit Regularization Action Free Offline Offline Policy Offline Multi Agent Reinforcement Learning Multi Agent MuJoCo

July 20, 2023

Exploring reinforcement learning techniques for discrete and continuous control tasks in the MuJoCo environment
Vaddadi Sai Rahul, Debajyoti Chakraborty
Reinforcement Learning Q Learning Continuous Control Deep Deterministic Policy Gradient Continuous Environment Continuous Control Task Multi Agent MuJoCo

June 19, 2023

Maximum Entropy Heterogeneous-Agent Reinforcement Learning
Jiarong Liu, Yifan Zhong, Siyi Hu, Haobo Fu, Qiang Fu, Xiaojun Chang, Yaodong Yang
Multi Agent Reinforcement Learning Maximum Entropy Multi Agent Challenge Multi Agent MuJoCo Multi Agent Particle Heterogeneous Multi Agent Reinforcement Learning

May 21, 2023

Unsupervised Discovery of Continuous Skills on a Sphere
Takahisa Imagawa, Takuya Hiraoka, Yoshimasa Tsuruoka
Spherical Surface Unsupervised Discovery Unsupervised Reinforcement Learning Multi Agent MuJoCo Diverse Skill Latent Skill

February 7, 2023

Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influence
Simin Li, Jun Guo, Jingqiao Xiu, Pu Feng, Xin Yu, Aishan Liu, Wenjun Wu, Xianglong Liu
Adversarial Attack Cooperative Multi Agent Reinforcement Learning Multi Agent Interaction Multi Agent MuJoCo Adversarial Influence

December 11, 2022

Off-Policy Deep Reinforcement Learning Algorithms for Handling Various Robotic Manipulator Tasks
Altun Rzayev, Vahid Tavakol Aghaei
Manipulation Task Robotic Manipulator Multi Agent MuJoCo Policy Deep Reinforcement Learning Efficient Control

November 28, 2022

Learning from Good Trajectories in Offline Multi-Agent Reinforcement Learning
Qi Tian, Kun Kuang, Furui Liu, Baoxiang Wang
LeArning Abstract Multi Agent Reinforcement Learning Multi Agent Action Free Offline Multi Agent Policy Offline Multi Agent Reinforcement Learning Multi Agent MuJoCo

Multi Agent MuJoCo

Papers

CPEG: Leveraging Consistency Policy with Consensus Guidance for Multi-agent Exploration

Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning

ComaDICE: Offline Cooperative Multi-Agent Reinforcement Learning with Stationary Distribution Shift Regularization

Learning to enhance multi-legged robot on rugged landscapes

MuJoCo MPC for Humanoid Control: Evaluation on HumanoidBench

Temporal Abstraction in Reinforcement Learning with Offline Data

Zero-Shot Transfer of Neural ODEs

Closed Loop Interactive Embodied Reasoning for Robot Manipulation

DeepSafeMPC: Deep Learning-Based Model Predictive Control for Safe Multi-Agent Reinforcement Learning

Open-Source Reinforcement Learning Environments Implemented in MuJoCo with Franka Manipulator

Similarity-based Knowledge Transfer for Cross-Domain Reinforcement Learning

FP3O: Enabling Proximal Policy Optimization in Multi-Agent Cooperation with Parameter-Sharing Versatility

Heterogeneous Multi-Agent Reinforcement Learning via Mirror Descent Policy Optimization

Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization

Exploring reinforcement learning techniques for discrete and continuous control tasks in the MuJoCo environment

Maximum Entropy Heterogeneous-Agent Reinforcement Learning

Unsupervised Discovery of Continuous Skills on a Sphere

Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influence

Off-Policy Deep Reinforcement Learning Algorithms for Handling Various Robotic Manipulator Tasks

Learning from Good Trajectories in Offline Multi-Agent Reinforcement Learning