Inverse Reinforcement Learning from a Gradient-based Learner

Abstract

Inverse Reinforcement Learning addresses the problem of inferring an expert's reward function from demonstrations. However, in many applications, we not only have access to the expert's near-optimal behavior, but we also observe part of her learning process. In this paper, we propose a new algorithm for this setting, in which the goal is to recover the reward function being optimized by an agent, given a sequence of policies produced during learning. Our approach is based on the assumption that the observed agent is updating her policy parameters along the gradient direction. Then we extend our method to deal with the more realistic scenario where we only have access to a dataset of learning trajectories. For both settings, we provide theoretical insights into our algorithms' performance. Finally, we evaluate the approach in a simulated GridWorld environment and on the MuJoCo environments, comparing it with the state-of-the-art baseline.

References in corpus (6)

• Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
• Equivalence Between Policy Gradients and Soft Q-Learning
• Parametric estimation. Finite sample theory
• Fast and Robust Least Squares Estimation in Corrupted Linear Models
• On-Policy Robot Imitation Learning from a Converging Supervisor
• Inverse Reinforcement Learning with Multiple Ranked Experts

Cited by in corpus (2)

• Inverse Contextual Bandits: Learning How Behavior Evolves over Time
• Learning from an Exploring Demonstrator: Optimal Reward Estimation for Bandits