Timezone: »

Non-Cooperative Inverse Reinforcement Learning
Xiangyuan Zhang · Kaiqing Zhang · Erik Miehling · Tamer Basar

Tue Dec 10 05:30 PM -- 07:30 PM (PST) @ East Exhibition Hall B + C #176

Making decisions in the presence of a strategic opponent requires one to take into account the opponent's ability to actively mask its intended objective. To describe such strategic situations, we introduce the non-cooperative inverse reinforcement learning (N-CIRL) formalism. The N-CIRL formalism consists of two agents with completely misaligned objectives, where only one of the agents knows the true objective function. Formally, we model the N-CIRL formalism as a zero-sum Markov game with one-sided incomplete information. Through interacting with the more informed player, the less informed player attempts to both infer, and act according to, the true objective function. As a result of the one-sided incomplete information, the multi-stage game can be decomposed into a sequence of single-stage games expressed by a recursive formula. Solving this recursive formula yields the value of the N-CIRL game and the more informed player's equilibrium strategy. Another recursive formula, constructed by forming an auxiliary game, termed the dual game, yields the less informed player's strategy. Building upon these two recursive formulas, we develop a computationally tractable algorithm to approximately solve for the equilibrium strategies. Finally, we demonstrate the benefits of our N-CIRL formalism over the existing multi-agent IRL formalism via extensive numerical simulation in a novel cyber security setting.

Author Information

Xiangyuan Zhang (University of Illinois at Urbana-Champaign)
Kaiqing Zhang (University of Illinois at Urbana-Champaign (UIUC))
Erik Miehling (University of Illinois at Urbana-Champaign)

I am a postdoctoral research associate in the Coordinated Science Lab at the University of Illinois at Urbana–Champaign working with Tamer Başar and Cédric Langbort. Prior to joining UIUC, I completed a PhD in Electrical Engineering: Systems at the University of Michigan under the guidance of Demos Teneketzis. My research interests concern game/decision theory, control theory, and reinforcement learning, and their applications to problems in cyber security and operations research.

Tamer Basar (University of Illinois at Urbana-Champaign)

More from the Same Authors