We propose a hybrid approach aimed at improving the sample efficiency in goal-directed reinforcement learning. We do this via a two-step mechanism where firstly, we approximate a model from Model-Free reinforcement learning. Then, we leverage this approximate model along with a notion of reachability using Mean First Passage Times to perform Model-Based reinforcement learning. Built on such a novel observation, we design two new algorithms - Mean First Passage Time based Q-Learning (MFPT-Q) and Mean First Passage Time based DYNA (MFPT-DYNA), that have been fundamentally modified from the state-of-the-art reinforcement learning techniques. Preliminary results have shown that our hybrid approaches converge with much fewer iterations than their corresponding state-of-the-art counterparts and therefore requiring much fewer samples and much fewer training trials to converge.
@article{arxiv.1901.01977,
title = {Accelerating Goal-Directed Reinforcement Learning by Model Characterization},
author = {Shoubhik Debnath and Gaurav Sukhatme and Lantao Liu},
journal= {arXiv preprint arXiv:1901.01977},
year = {2019}
}
Comments
The paper was published in 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)