상세정보
학술대회
Multiagent Reinforcement Learning in Escape Scenario
- 발행일
- 201810
- 출처
- International Conference on Information and Communication Technology Convergence (ICTC) 2018, pp.1031-1033
- 협약과제
- 18ZH1100, 사물-사람-공간의 유기적 연결을 위한 초연결 공간의 분산 지능 핵심원천 기술, 손영성
- 초록
- Reinforcement learning let agents perform repeated actions in given environments and identify how to behave in the given environments. In this paper, we showed possibilities of solutions for real-world scenarios on multiagent reinforcement learning environment. Our experiment showed an approach to investigate a way for agents to escape in an escape scenario using multiagent reinforcement learning. Two types of agents are trained. We trained Escaper Agent to find an optimal exit which increases a total number of escaped agents and decreases congestion and Exit Agent to find optimal locations for exits. Thoroughly setting reward function could simulate real-world problems and get insights on how to break down challenging questions.
- KSP 제안 키워드
- Break-down, Learning Environment, Real-World Problems, Reinforcement Learning(RL), multi-agent reinforcement learning, reward function