BROWSE
Detail
Conference Paper
Multiagent Reinforcement Learning in Escape Scenario
Cited 0 time in 
Share 
Share
- Authors
- Donghun Lee, Seonghyun Kim, Young-Sung Son
- Issue Date
- 2018-10
- Citation
- International Conference on Information and Communication Technology Convergence (ICTC) 2018, pp.1031-1033
- Publisher
- IEEE
- Language
- English
- Type
- Conference Paper
- Abstract
- 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 Keywords
- Break down, Learning Environment, Real-World Problems, Reinforcement Learning(RL), multi-agent reinforcement learning, reward function