Inverse Reinforcement Learning from a Gradient-based Learner
This addresses the inverse reinforcement learning problem for AI and robotics by leveraging learning trajectories, offering an incremental improvement over existing methods.
The paper tackles the problem of inferring an expert's reward function by observing not just optimal behavior but also part of the learning process, proposing a gradient-based algorithm that recovers the reward from a sequence of policies and achieves competitive performance in simulated GridWorld and MuJoCo environments.
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.