Dynamic Observation Policies in Observation Cost-Sensitive Reinforcement Learning

Published: 28 Oct 2023, Last Modified: 28 Oct 2023WANT@NeurIPS 2023 PosterEveryoneRevisionsBibTeX
Keywords: Reinforcement Learning, DQN, Sensing and Observation Costs, Observation Efficiency, Noiselessly Observable Markov Decision Processes
TL;DR: This work proposes a reinforcement learning algorithm that enables the agent to learn to reduce its decision steps and costs associated with measuring the state of the environment.
Abstract: Reinforcement learning (RL) has been shown to learn sophisticated control policies for complex tasks including games, robotics, heating and cooling systems and text generation. The action-perception cycle in RL, however, generally assumes that a measurement of the state of the environment is available at each time step without a cost. In applications such as materials design, deep-sea and planetary robot exploration and medicine, however, there can be a high cost associated with measuring, or even approximating, the state of the environment. In this paper, we survey the recently growing literature that adopts the perspective that an RL agent might not need, or even want, a costly measurement at each time step. Within this context, we propose the Deep Dynamic Multi-Step Observationless Agent (DMSOA), contrast it with the literature and empirically evaluate it on OpenAI gym and Atari Pong environments. Our results, show that DMSOA learns a better policy with fewer decision steps and measurements than the considered alternative from the literature.
Submission Number: 27