상세정보
학술지
Avoiding Collaborative Paradox in Multi-agent Reinforcement Learning
- 발행일
- 202112
- 출처
- ETRI Journal, v.43 no.6, pp.1004-1012
- ISSN
- 1225-6463
- 출판사
- 한국전자통신연구원 (ETRI)
- 협약과제
- 21ZR1100, 자율적으로 연결·제어·진화하는 초연결 지능화 기술 연구, 박준희
- 초록
- The collaboration productively interacting between multi-agents has become an emerging issue in real-world applications. In reinforcement learning, multi-agent environments present challenges beyond tractable issues in single-agent settings. This collaborative environment has the following highly complex attributes: sparse rewards for task completion, limited communications between each other, and only partial observations. In particular, adjustments in an agent's action policy result in a nonstationary environment from the other agent's perspective, which causes high variance in the learned policies and prevents the direct use of reinforcement learning approaches. Unexpected social loafing caused by high dispersion makes it difficult for all agents to succeed in collaborative tasks. Therefore, we address a paradox caused by the social loafing to significantly reduce total returns after a certain timestep of multi-agent reinforcement learning. We further demonstrate that the collaborative paradox in multi-agent environments can be avoided by our proposed effective early stop method leveraging a metric for social loafing.
- KSP 제안 키워드
- Collaborative environment, Collaborative task, High dispersion, Learning approach, Nonstationary Environment, Real-world applications, Reinforcement Learning(RL), multi-agent reinforcement learning, partial observations, social loafing, task completion
본 저작물은 공공누리 제4유형 : 출처표시 + 상업적 이용금지 + 변경금지 조건에 따라 이용할 수 있습니다.
