Agent Strategy

Agent strategy research focuses on developing algorithms enabling autonomous agents to effectively coordinate, compete, and adapt within multi-agent systems, particularly in scenarios with incomplete information or adversarial interactions. Current research emphasizes methods like multi-agent reinforcement learning (MARL) enhanced by techniques such as optimal transport theory for resource allocation and policy alignment, and novel approaches to clustering and interpreting agent behaviors from observational data, even with anonymous agents. These advancements are crucial for building robust and explainable AI systems applicable to diverse domains, including robotics, finance, and traffic management, by improving coordination, resource efficiency, and adaptability in complex dynamic environments.

Papers

September 19, 2024

Learning to Coordinate without Communication under Incomplete Information
Shenghui Chen, Shufang Zhu, Giuseppe De Giacomo, Ufuk Topcu
LeArning Abstract Timely Communication Incomplete Information Cooperative Game Agent Strategy Deterministic Strategy

March 17, 2024

Bridging the Gap between Discrete Agent Strategies in Game Theory and Continuous Motion Planning in Dynamic Environments
Hongrui Zheng, Zhijun Zhuang, Stephanie Wu, Shuo Yang, Rahul Mangharam
Multi Agent Dynamic Environment Game Theory Policy Switching Agent Strategy

January 18, 2024

The Synergy Between Optimal Transport Theory and Multi-Agent Reinforcement Learning
Ali Baheri, Mykel J. Kochenderfer
Multi Agent Reinforcement Learning Optimal Transport Multi Agent Learning Model Synergy Policy Alignment Agent Strategy

January 10, 2024

Transparency as Delayed Observability in Multi-Agent Systems
Kshama Dwarakanath, Svitlana Vyetrenko, Toks Oyebode, Tucker Balch
Multi Agent Reinforcement Learning Multi Agent System Transparency Index Full Observability Agent Strategy

February 23, 2023

K-SHAP: Policy Clustering Algorithm for Anonymous Multi-Agent State-Action Pairs
Andrea Coletta, Svitlana Vyetrenko, Tucker Balch
Imitation Learning Agent Behavior Learning Agent Fusion SHAP Agent Strategy Policy Similarity

November 8, 2022

Policy-Based Reinforcement Learning for Assortative Matching in Human Behavior Modeling
Ou Deng, Qun Jin
Reinforcement Learning Multi Agent Reinforcement Learning Human Behavior Network Community Agent Strategy

September 26, 2022

Learning to simulate realistic limit order book markets from data as a World Agent
Andrea Coletta, Aymeric Moulin, Svitlana Vyetrenko, Tucker Balch
LeArning Abstract Raw Data Agent Smith Multi Agent Market Agent Tuning Market Simulator Agent Strategy Agent Simulation

August 17, 2022

A Framework for Understanding and Visualizing Strategies of RL Agents
Pedro Sequeira, Daniel Elenius, Jesse Hostetler, Melinda Gervasio
New Framework Human Understanding Reinforcement Learning Agent Agent Behavior Sequential Decision Making Task RL Agent Strategy Discovery Visualization Method Agent Strategy

March 8, 2022

On-the-fly Strategy Adaptation for ad-hoc Agent Coordination
Jaleh Zand, Jack Parker-Holder, Stephen J. Roberts
Multi Agent Reinforcement Learning AI Agent Self Play Multi Agent Coordination Agent Strategy Dynamic Strategy

January 5, 2022

Conditional Imitation Learning for Multi-Agent Games
Andy Shih, Stefano Ermon, Dorsa Sadigh
Multi Agent AI Agent Multi Agent Learning Multi Agent Imitation Agent Strategy Conditional Imitation

Agent Strategy

Papers

Learning to Coordinate without Communication under Incomplete Information

Bridging the Gap between Discrete Agent Strategies in Game Theory and Continuous Motion Planning in Dynamic Environments

The Synergy Between Optimal Transport Theory and Multi-Agent Reinforcement Learning

Transparency as Delayed Observability in Multi-Agent Systems

K-SHAP: Policy Clustering Algorithm for Anonymous Multi-Agent State-Action Pairs

Policy-Based Reinforcement Learning for Assortative Matching in Human Behavior Modeling

Learning to simulate realistic limit order book markets from data as a World Agent

A Framework for Understanding and Visualizing Strategies of RL Agents

On-the-fly Strategy Adaptation for ad-hoc Agent Coordination

Conditional Imitation Learning for Multi-Agent Games