Non-cooperative Inverse Reinforcement Learning

Abstract

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, construc

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhang2019non

Related papers

• Cooperative Inverse Reinforcement Learning (2016)0.00
• Inverse-inverse Reinforcement Learning. How To Hide Strategy From An Adversarial Inverse Reinforcement Learner (2022)7.50
• An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning (2018)0.00
• Interactive Inverse Reinforcement Learning For Cooperative Games (2021)0.00
• Data-driven Inverse Reinforcement Learning For Expert-learner Zero-sum Games (2023)0.00
• Multi-agent Inverse Reinforcement Learning For Certain General-sum Stochastic Games (2018)10.97
• Multi-agent Inverse Reinforcement Learning: Suboptimal Demonstrations And Alternative Solution Concepts (2021)0.00
• Reinforcement Learning And Inverse Reinforcement Learning With System 1 And System 2 (2018)7.16