Single Agent Learning

Single-agent learning focuses on training a single artificial agent to perform a task, but recent research increasingly explores how multiple agents can learn and collaborate more effectively. Current research emphasizes efficient information sharing strategies among agents, including parameter sharing and action recommendations, and investigates the use of reinforcement learning algorithms, diffusion models, and evolutionary approaches to improve both individual and collective performance. These advancements are significant because they enable more robust and efficient solutions to complex problems in various domains, from robotics and autonomous vehicles to decentralized decision-making systems.

Papers

May 23, 2024

Distributed Continual Learning
Long Le, Marcel Hussing, Eric Eaton
Continual LEArning Agent Performance Agent Model Single Agent Learning

December 15, 2023

Peer Learning: Learning Complex Policies in Groups from Scratch via Action Recommendations
Cedric Derstroff, Mattia Cerrato, Jannis Brugger, Jan Peters, Stefan Kramer
Multi Armed Bandit Group Setting Scratch Project Policy Design Standard Reinforcement Learning Peer Learning Single Agent Learning Action Recommendation

December 8, 2023

DARLEI: Deep Accelerated Reinforcement Learning with Evolutionary Intelligence
Saeejith Nair, Mohammad Javad Shafiee, Alexander Wong
Reinforcement Learning Single Agent Learning Evolutionary Learning Multi Generational Selection

October 25, 2023

MACP: Efficient Model Adaptation for Cooperative Perception
Yunsheng Ma, Juanwu Lu, Can Cui, Sicheng Zhao, Xu Cao, Wenqian Ye, Ziran Wang
Single Agent Cooperative Perception Multi Agent Perception Single Agent Learning Efficient Model Adaptation

September 14, 2023

Deep Multi-Agent Reinforcement Learning for Decentralized Active Hypothesis Testing
Hadar Szostak, Kobi Cohen
Multi Agent Reinforcement Learning Multi Agent Policy Single Agent Learning Active Hypothesis Testing

June 12, 2023

A Black-box Approach for Non-stationary Multi-agent Reinforcement Learning
Haozhe Jiang, Qiwen Cui, Zhihan Xiong, Maryam Fazel, Simon S. Du
Black Box Nash Equilibrium Markov Game Multi Agent Learning Single Agent Learning

May 27, 2023

MADiff: Offline Multi-agent Learning with Diffusion Models
Zhengbang Zhu, Minghuan Liu, Liyuan Mao, Bingyi Kang, Minkai Xu, Yong Yu, Stefano Ermon, Weinan Zhang
Diffusion Model Multi Agent Learning Multi Agent Interaction Offline Multi Agent Reinforcement Learning Single Agent Learning

March 23, 2023

Decentralized Adversarial Training over Graphs
Ying Cao, Elsa Rizk, Stefan Vlaski, Ali H. Sayed
Adversarial Attack Graph Drawing Adversarial Training Diffusion Learning Single Agent Learning

October 28, 2022

Game-Theoretical Perspectives on Active Equilibria: A Preferred Solution Concept over Nash Equilibria
Dong-Ki Kim, Matthew Riemer, Miao Liu, Jakob N. Foerster, Gerald Tesauro, Jonathan P. How
Nash Equilibrium Game Theoretic Efficient Equilibrium Single Agent Learning Solved Problem

October 21, 2022

Competing Bandits in Time Varying Matching Markets
Deepan Muthirayan, Chinmay Maheshwari, Pramod P. Khargonekar, Shankar Sastry
Sub Linear Regret Single Agent Learning Matching Market

August 18, 2022

Communication-Efficient Collaborative Best Arm Identification
Nikolai Karpov, Qin Zhang
Multi Agent Bandit Algorithm Multi Agent Learning Best Arm Identification Single Agent Learning

January 20, 2022

Safety-Aware Multi-Agent Apprenticeship Learning
Junchen Zhao
Inverse Reinforcement Learning Multi Agent Learning Safe Multi Agent Reinforcement Learning Apprenticeship Learning Single Agent Learning