Skip to yearly menu bar Skip to main content


Poster

Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning

Tom Zahavy · Matan Haroush · Nadav Merlis · Daniel J Mankowitz · Shie Mannor

Room 517 AB #114

Keywords: [ Reinforcement Learning and Planning ] [ Natural Language Processing ] [ Game Playing ]


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 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.

Live content is unavailable. Log in and register to view live content