Date of Award
5-2025
Degree Type
Masters Thesis
Degree Name
Master of Science (MS)
School
Computing Sciences and Computer Engineering
Committee Chair
Dr. Bikramjit Banerjee
Committee Chair School
Computing Sciences and Computer Engineering
Committee Member 2
Dr. Andrew Sung
Committee Member 2 School
Computing Sciences and Computer Engineering
Committee Member 3
Dr. Bo Li
Committee Member 3 School
Computing Sciences and Computer Engineering
Abstract
Inverse reinforcement learning (IRL) has emerged as a popular approach for training robots from human/expert demonstration, where a learner/robot infers the expert's hidden reward function using the demonstrations and a simulator. We argue that noise is inevitable in certain parts of the demonstration, and show that such noise does indeed deteriorate the performance of a popular and widely applied IRL method, called Adversarial IRL (AIRL). To render AIRL robust to noise, we formulate the problem of reward inference as one of log-likelihood optimization that accommodates noisy input. We adopt two techniques from the literature on learning hidden representations in sequential decision tasks and combine them with AIRL to solve this unified optimization problem. Experiments in four benchmark OpenAI Gym environments show that our proposed methods are effective in overcoming demonstration noise for the task of reward learning, but less so for the task of reproducing the expert behavior.
ORCID ID
0009-0003-2565-5310
Copyright
Sagar Shrestha, 2025
Recommended Citation
Shrestha, Sagar, "Adversarial Inverse Reinforcement Learning with Noisy Observations" (2025). Master's Theses. 1110.
https://aquila.usm.edu/masters_theses/1110
Included in
Artificial Intelligence and Robotics Commons, Other Computer Engineering Commons, Probability Commons, Robotics Commons