State Space Decomposition and Subgoal Creation for Transfer in Deep Reinforcement Learning
Abstract
Typical reinforcement learning (RL) agents learn to complete tasks specified by reward functions tailored to their domain. As such, the policies they learn do not generalize even to similar domains. To address this issue, we develop a framework through which a deep RL agent learns to generalize policies from smaller, simpler domains to more complex ones using a recurrent attention mechanism. The task is presented to the agent as an image and an instruction specifying the goal. This meta-controller guides the agent towards its goal by designing a sequence of smaller subtasks on the part of the state space within the attention, effectively decomposing it. As a baseline, we consider a setup without attention as well. Our experiments show that the meta-controller learns to create subgoals within the attention.
Keywords
Cite
@article{arxiv.1705.08997,
title = {State Space Decomposition and Subgoal Creation for Transfer in Deep Reinforcement Learning},
author = {Himanshu Sahni and Saurabh Kumar and Farhan Tejani and Yannick Schroecker and Charles Isbell},
journal= {arXiv preprint arXiv:1705.08997},
year = {2017}
}
Comments
5 pages, 6 figures; 3rd Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM 2017), Ann Arbor, Michigan