Balancing Teacher Following and Reward Maximization in Reinforcement Learning
Name
shenfeldamit-idanshen-sm-eecs-2024-thesis.pdf
Description
Thesis PDF
Size
2.02 MB
Format
Adobe PDF
Checksum (MD5)
2fc8ba97da4032e791919ac0eb7fd664
Author(s)
Shenfeld Amit, Idan
Advisor(s)
Agrawal, Pulkit
Date Issued
May 2024
Publisher
Massachusetts Institute of Technology
Abstract
Learning from rewards (i.e., reinforcement learning or RL) and learning to imitate a teacher (i.e., teacher-student learning) are two established approaches for solving sequential decision-making problems. To combine the benefits of these different forms of learning, it is common to train a policy to maximize a combination of reinforcement and teacher-student learning objectives. However, without a principled method to balance these objectives, prior work used heuristics and problem-specific hyperparameter searches to balance the two objectives. We present a principled approach, along with an approximate implementation for dynamically and automatically balancing when to follow the teacher and when to use rewards. The main idea is to adjust the importance of teacher supervision by comparing the agent’s performance to the counterfactual scenario of the agent learning without teacher supervision and only from rewards. If using teacher supervision improves performance, the importance of teacher supervision is increased and otherwise it is decreased. We will investigate the capabilities of this algorithm against strong baselines across diverse domains.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)
Copyright retained by author(s)
Persistent DSpace Link
