Autonomy Talks - Kyriakos Vamvoudakis: Bounded Rationality Methods in RL-driven Autonomy

Autonomy Talks - 18/01/2022

Speaker: Prof. Kyriakos Vamvoudakis, Georgia Institute of Technology

Title: Bounded Rationality Methods in Reinforcement Learning-driven Autonomy

Abstract: Autonomous systems will be tasked with operating in complex, human-centric environ- ments both in cooperation and in competition with humans and other agents. In this talk, issues of prediction in the context of game theory and multi-agent cyber-physical systems will be addressed. To account for the cognitive limitations of human and machine decision-makers, we introduce ideas and principles of bounded rationality for autonomy using tools from control theory and reinforcement learning. Specifically, we will formulate level-k thinking and cognitive hierarchy models in nonlinear and linear noncooperative differential games, where each agent is assigned an intelligence level corresponding to a number of thinking iterations. The applicability of this approach will be highlighted via the example of a pursuit evasion game between Unmanned Aerial Vehicles. The versa- tility of the proposed methods will be shown via results of level-k thinking in discrete stochastic games. Finally, in order to design more advanced decision-making algorithms that explicitly exploit the learning abilities of the other agents in the environment, a meta-learning framework in games will be presented, via which an autonomous agent can achieve learning manipulation and deception.