5 papers
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…
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…
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…
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…
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…