Teaching Inverse Reinforcement Learners via Features and Demonstrations
This addresses a key limitation in inverse reinforcement learning for agents with incomplete or incorrect feature knowledge, though it is incremental as it builds on existing algorithms.
The paper tackles the problem of learning from demonstrations when the learner and expert have mismatched worldviews, by introducing the teaching risk to measure potential suboptimality and showing that bounds on it enable near-optimal policy learning using standard inverse reinforcement learning algorithms.
Learning near-optimal behaviour from an expert's demonstrations typically relies on the assumption that the learner knows the features that the true reward function depends on. In this paper, we study the problem of learning from demonstrations in the setting where this is not the case, i.e., where there is a mismatch between the worldviews of the learner and the expert. We introduce a natural quantity, the teaching risk, which measures the potential suboptimality of policies that look optimal to the learner in this setting. We show that bounds on the teaching risk guarantee that the learner is able to find a near-optimal policy using standard algorithms based on inverse reinforcement learning. Based on these findings, we suggest a teaching scheme in which the expert can decrease the teaching risk by updating the learner's worldview, and thus ultimately enable her to find a near-optimal policy.