ETRI-Knowledge Sharing Plaform



논문 검색
구분 SCI
연도 ~ 키워드


학술대회 A Sim2real Framework Enabling Decentralized Agents to Execute MADDPG Tasks
Cited 0 time in scopus Download 2 time Share share facebook twitter linkedin kakaostory
서영호, 우성필, 김현학, 박동환
Workshop on Distributed Infrastructures for Deep Learning (DIDL) 2019, pp.1-6
19ZH1100, 사물-사람-공간의 유기적 연결을 위한 초연결 공간의 분산 지능 핵심원천 기술, 박준희
Multi-agent RL is a process of training the agents to collaborate with others. We argue that an additional?셱eality gap?? in the system aspects occurs when applying sim2real to the multi-agent RL, especially when performing the?셳ransferred?? collaborative task in the real-world environment. In this paper, we propose an ADO framework enabling decentralized agents to participate in performing collaborative tasks without suffering from the reality gap. Our contribution is threefold. First, we clearly identify and summarize the reality gaps in the context of the sim2real of multi-agent RL. Second, we propose a new system model to deal with system issues derived from when executing collaborative tasks. Third, we design and implement a software framework to support system issues required in developing and executing collaborative tasks in the real world.
Decentralized system, Deep Learning Framework, Multi-Agent Reinforcement Learning, Sim2Real
KSP 제안 키워드
Collaborative task, Decentralized agents, Deep learning framework, Real-world, Reality gap, Reinforcement Learning(RL), Software Framework, decentralized system, deep learning(DL), multi-agent reinforcement learning, support system