ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술지 Utilizing Hidden Observations to Enhance the Performance of the Trained Agent
Cited 0 time in scopus Download 6 time Share share facebook twitter linkedin kakaostory
저자
장수영, 이주형
발행일
202207
출처
IEEE Robotics and Automation Letters, v.7 no.3, pp.7858-7864
ISSN
2377-3766
출판사
IEEE
DOI
https://dx.doi.org/10.1109/LRA.2022.3186508
협약과제
22ZR1100, 자율적으로 연결·제어·진화하는 초연결 지능화 기술 연구, 박준희
초록
The frame-skipping strategy has been widely employed in deep reinforcement learning (DRL) technology to train an agent. Specifically, this strategy repeats the action determined by the agent for a fixed number of frames. It increases computational efficiency by reducing the number of inferences by making the action decision sparse. However, previously, these consecutive changes in frames during the frame-skipping were hidden and ignored from the environment and did not affect the agent's action decision. As a result, it can adversely affect the performance of trained agents, where the performance is more critical than computational efficiency. To alleviate these issues, we propose a new framework that utilizes these hidden frames during the frame-skipping, called $hidden$ $observation$, to enhance the performance of the trained agent. The proposed framework retrieves all hidden observations during frame skipping. It then combines batch inference and an exponentially weighted sum to calculate and merge the outputs from hidden observations. Through experiments, we validated the effectiveness of the proposed method in terms of both performance and stability with only a marginal increase in computation.
KSP 제안 키워드
Computational Efficiency, Deep reinforcement learning, Frame skipping, Reinforcement Learning(RL), Skipping strategy, weighted sum