상세정보
학술지
Prioritized Environment Configuration for Drone Control with Deep Reinforcement Learning
- 저자
- 장수영, 최창범
- 발행일
- 202201
- 출처
- Human-centric Computing and Information Sciences, v.12, pp.1-16
- ISSN
- 2192-1962
- 출판사
- KIPS-CSWRG
- 협약과제
- 21ZR1100, 자율적으로 연결·제어·진화하는 초연결 지능화 기술 연구, 박준희
- 초록
- In reinforcement learning, first, the agent collects experiences by interacting with the environment through trial-and-errors (experience collection stage) and then learns from the collected experiences (learning stage). This two-stage training process repeats until the agent solves a given task and requires a lot of experience, computation power, and time for training the agent. Therefore, many studies are conducted to improve the training speed and performance to mitigate them, focusing on the learning stage. This paper focuses on the experience collection stage and proposes a prioritized environment configuration that prioritizes and stochastically samples the effective configuration for initializing the environment for every episode. Therefore, we can provide the environments initialized with the configuration suitable for effective experience collection to the agent. The proposed algorithm can complement the reinforcement learning algorithms that focus on the learning stage. We have shown speed and performance improvement by applying the prioritized environment configuration to an autonomous drone flight simulator. In addition, the results show that the proposed algorithm works well with both on-policy and off-policy reinforcement learning algorithms in distributed framework with multiple workers
- KSP 제안 키워드
- Computation power, Deep reinforcement learning, Distributed framework, Effective configuration, Flight Simulator, Learning Stage, Off-policy reinforcement learning, Reinforcement Learning(RL), Training speed, Two-Stage, learning algorithms
본 저작물은 크리에이티브 커먼즈 저작자 표시 - 비영리 (CC BY NC) 조건에 따라 이용할 수 있습니다.
