Preference elicitation and inverse reinforcement learning

2011/04/29 by Constantin A. Rothkopf, Rothkopf, Constantin, Christos Dimitrakakis +1 · 2 citations
Computer Science · #Advanced Multi-Objective Optimization Algorithms #Evolutionary Algorithms and Applications #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Reinforcement Learning in Robotics

paper · pdf · doi:10.48550/arxiv.1104.5687

openalex publication_date 2011/04/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We state the problem of inverse reinforcement learning in terms of preference elicitation, resulting in a principled (Bayesian) statistical formulation. This generalises previous work on Bayesian inverse reinforcement learning and allows us to obtain a posterior distribution on the agent's preferences, policy and optionally, the obtained reward sequence, from observations. We examine the relation of the resulting approach to other statistical methods for inverse reinforcement learning via analysis and experimental results. We show that preferences can be determined accurately, even if the observed agent's policy is sub-optimal with respect to its own preferences. In that case, significantly improved policies with respect to the agent's preferences are obtained, compared to both other methods and to the performance of the demonstrated policy.

Cited by

• Inference of Altruism and Intrinsic Rewards in Multi-Agent Systems
• The Limits of Predicting Agents from Behaviour

Related

• Inverse Reinforcement Learning using Revealed Preferences and Passive Stochastic Optimization
• Inverse Reinforcement Learning with Explicit Policy Estimates
• Inverse Reinforcement Learning with Conditional Choice Probabilities
• Quantifying the Sensitivity of Inverse Reinforcement Learning to Misspecification
• A General Theoretical Paradigm to Understand Learning from Human Preferences