Maximum Entropy Multi-Task Inverse RL

Abstract

Multi-task IRL allows for the possibility that the expert could be switching between multiple ways of solving the same problem, or interleaving demonstrations of multiple tasks. The learner aims to learn the multiple reward functions that guide these ways of solving the problem. We present a new method for multi-task IRL that generalizes the well-known maximum entropy approach to IRL by combining it with the Dirichlet process based clustering of the observed input. This yields a single nonlinear optimization problem, called MaxEnt Multi-task IRL, which can be solved using the Lagrangian relaxation and gradient descent methods. We evaluate MaxEnt Multi-task IRL in simulation on the robotic task of sorting onions on a processing line where the expert utilizes multiple ways of detecting and removing blemished onions. The method is able to learn the underlying reward functions to a high level of accuracy and it improves on the previous approaches to multi-task IRL.

References in corpus (6)

• Generative Adversarial Imitation Learning
• Maximum Entropy Deep Inverse Reinforcement Learning
• Bayesian multitask inverse reinforcement learning
• Multi-Modal Imitation Learning from Unstructured Demonstrations using Generative Adversarial Nets
• Multi-task Maximum Entropy Inverse Reinforcement Learning
• A Framework and Method for Online Inverse Reinforcement Learning