BROWSE
Detail
Conference Paper
강화 학습 에이전트의 개성 부여를 유도하는 내재적 보상 방법 연구
Cited - time in 
Share 
Share
- Issue Date
- 2022-07
- Citation
- 대한전자공학회 학술 대회 (하계) 2022, pp.2283-2286
- Publisher
- 대한전자공학회
- Language
- Korean
- Type
- Conference Paper
- Abstract
- Recently, reinforcement learning has solved problems through intrinsic reward methods. In this study, we propose a method of giving individuality to agents to solve the problem of the diversity of multiple agents. The proposed method induces agents to have individuality while learning adversarially to the reward model. Experimental results show that the proposed agent has a behavior pattern according to the personality vector.
- KSP Keywords
- Behavior pattern, Multiple Agents, Reinforcement learning(RL)