Switching the Loss Reduces the Cost in Batch Reinforcement Learning
Alex Ayoub, Kaiwen Wang, Vincent Liu, Samuel Robertson, James McInerney, Dawen Liang, Nathan Kallus, Csaba Szepesvari
Abstract
We propose training fitted Q-iteration with log-loss (FQI-LOG) for batch reinforcement learning (RL). We show that the number of samples needed to learn a near-optimal policy with FQI-LOG scales with the accumulated cost of the optimal policy, which is zero in problems where acting optimally achieves the goal and incurs no cost. In doing so, we provide a general framework for proving small-cost bounds, i.e. bounds that scale with the optimal achievable cost, in batch RL. Moreover, we empirically verify that FQI-LOG uses fewer samples than FQI trained with squared loss on problems where the optimal policy reliably achieves the goal.
BibTeX
@inproceedings{
ayoub2024switching,
title={Switching the Loss Reduces the Cost in Batch Reinforcement Learning},
author={Alex Ayoub and Kaiwen Wang and Vincent Liu and Samuel Robertson and James McInerney and Dawen Liang and Nathan Kallus and Csaba Szepesvari},
booktitle={Forty-first International Conference on Machine Learning},
year={2024},
url={https://openreview.net/forum?id=7PXSc5fURu}
}