Boosting Soft Q-Learning by Bounding
Machine Learning
2024-06-27 v1 Artificial Intelligence
Machine Learning
Abstract
An agent's ability to leverage past experience is critical for efficiently solving new tasks. Prior work has focused on using value function estimates to obtain zero-shot approximations for solutions to a new task. In soft Q-learning, we show how any value function estimate can also be used to derive double-sided bounds on the optimal value function. The derived bounds lead to new approaches for boosting training performance which we validate experimentally. Notably, we find that the proposed framework suggests an alternative method for updating the Q-function, leading to boosted performance.
Cite
@article{arxiv.2406.18033,
title = {Boosting Soft Q-Learning by Bounding},
author = {Jacob Adamczyk and Volodymyr Makarenko and Stas Tiomkin and Rahul V. Kulkarni},
journal= {arXiv preprint arXiv:2406.18033},
year = {2024}
}
Comments
To appear in the 1st Reinforcement Learning Conference