Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning
Machine Learning
2019-02-26 v3 Machine Learning
Abstract
Learning how to act when there are many available actions in each state is a challenging task for Reinforcement Learning (RL) agents, especially when many of the actions are redundant or irrelevant. In such cases, it is sometimes easier to learn which actions not to take. In this work, we propose the Action-Elimination Deep Q-Network (AE-DQN) architecture that combines a Deep RL algorithm with an Action Elimination Network (AEN) that eliminates sub-optimal actions. The AEN is trained to predict invalid actions, supervised by an external elimination signal provided by the environment. Simulations demonstrate a considerable speedup and added robustness over vanilla DQN in text-based games with over a thousand discrete actions.
Cite
@article{arxiv.1809.02121,
title = {Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning},
author = {Tom Zahavy and Matan Haroush and Nadav Merlis and Daniel J. Mankowitz and Shie Mannor},
journal= {arXiv preprint arXiv:1809.02121},
year = {2019}
}