ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술대회 Combining Reward Shaping and Curriculum Learning for Training Agents with High Dimensional Continuous Action Spaces
Cited 7 time in scopus Download 7 time Share share facebook twitter linkedin kakaostory
저자
장수영, 한미경
발행일
201810
출처
International Conference on Information and Communication Technology Convergence (ICTC) 2018, pp.1391-1393
DOI
https://dx.doi.org/10.1109/ICTC.2018.8539438
협약과제
18ZH1100, 사물-사람-공간의 유기적 연결을 위한 초연결 공간의 분산 지능 핵심원천 기술, 손영성
초록
The needs for training agent with high dimensional continuous action spaces will increase as the robot hardware such as robotic arms and humanoid robots are becoming more and more sophisticated. However, it is difficult and time-consuming task. To tackle the problem, we combine reward shaping and curriculum learning. More specifically, the rewards are provided to the agent for every step it takes and the difficulty of the problem gradually increases depending on the agent learning. Both reward function and curriculum are designed to make the agent achieve its objective. The simulation results demonstrate that the proposed scheme outperforms the comparisons.
KSP 제안 키워드
Continuous action, Curriculum learning, High-dimensional, Robotic arm, humanoid robot, reward function, robot hardware, simulation results