Min-Max Entropy Inverse RL of Multiple Tasks
Document Type
Conference Proceeding
Publication Date
5-30-2021
School
Computing Sciences and Computer Engineering
Abstract
Multi-task IRL recognizes that expert(s) could be switching between multiple ways of solving the same problem, or interleaving demonstrations of multiple tasks. The learner aims to learn the reward functions that individually guide these distinct ways. We present a new method for multi-task IRL that generalizes the well-known maximum entropy approach by combining it with a Dirichlet process based minimum entropy clustering of the observed data. This yields a single nonlinear optimization problem, called MinMaxEnt Multi-task IRL (MME-MTIRL), which can be solved using the Lagrangian relaxation and gradient descent methods. We evaluate MME-MTIRL 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.
Publication Title
2021 IEEE International Conference On Robotics and Automation (ICRA)
Recommended Citation
Arora, S.,
Doshi, P.,
Banerjee, B.
(2021). Min-Max Entropy Inverse RL of Multiple Tasks. 2021 IEEE International Conference On Robotics and Automation (ICRA).
Available at: https://aquila.usm.edu/fac_pubs/20615
COinS