タスク・環境適応型強化学習によるロボット制御
Task and Domain Adaptive Reinforcement Learning for Robot Control
転移学習を活用し、異なるタスクや環境変化に動的に適応する強化学習エージェントを提案し、飛行船制御で実世界へのゼロショット転移を実証した。
著者: Yu Tang Liu, Nilaksh Singh, Aamir Ahmad
分類: cs.RO, cs.AI, cs.SY, eess.SY
原文アブストラクト
Deep reinforcement learning (DRL) has shown remarkable success in simulation domains, yet its application in designing robot controllers remains limited, due to its single-task orientation and insufficient adaptability to environmental changes. To overcome these limitations, we present a novel adaptive agent that leverages transfer learning techniques to dynamically adapt policy in response to different tasks and environmental conditions. The approach is validated through the blimp control challenge, where multitasking capabilities and environmental adaptability are essential. The agent is trained using a custom, highly parallelized simulator built on IsaacGym. We perform zero-shot transfer to fly the blimp in the real world to solve various tasks. We share our code at https://github.com/robot-perception-group/adaptive_agent.
