Dynamic Observation Policies in Observation Cost-Sensitive Reinforcement Learning

arXiv:2307.02620v3 Announce Type: replace
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 …

abstract arxiv control cooling cost cs.ai cs.lg dynamic environment games however learn measurement observation perception policies reinforcement reinforcement learning robotics state systems tasks text text generation the environment type