activity
20182021
collaborators

5 papers

cs.LG2021

Inverse Reinforcement Learning for Strategy Identification

Mark Rucker, Stephen Adams, Roy Hayes +1

In adversarial environments, one side could gain an advantage by identifying the opponent's strategy. For example, in combat games, if an opponents strategy is identified as overly…

cs.CR2020

Cyberphysical Security Through Resiliency: A Systems-centric Approach

Cody Fleming, Carl Elks, Georgios Bakirtzis +4

Cyber-physical systems (CPS) are often defended in the same manner as information technology (IT) systems -- by using perimeter security. Multiple factors make such defenses insuff…

cs.AI2020

Value-Decomposition Multi-Agent Actor-Critics

Jianyu Su, Stephen Adams, Peter A. Beling

The exploitation of extra state information has been an active research area in multi-agent reinforcement learning (MARL). QMIX represents the joint action-value using a non-negati…

cs.AI2020

Counterfactual Multi-Agent Reinforcement Learning with Graph Convolution Communication

Jianyu Su, Stephen Adams, Peter A. Beling

We consider a fully cooperative multi-agent system where agents cooperate to maximize a system's utility in a partial-observable environment. We propose that multi-agent systems mu…

cs.LG2018

Multi-agent Inverse Reinforcement Learning for Certain General-sum Stochastic Games

Xiaomin Lin, Stephen C. Adams, Peter A. Beling

This paper addresses the problem of multi-agent inverse reinforcement learning (MIRL) in a two-player general-sum stochastic game framework. Five variants of MIRL are considered: u…