Tactile Curiosity Drives Robot Interaction
아직 한국어판이 없어 영어 원문으로 표시.
초록 발췌
Mastering robot manipulation skills via reinforcement learning (RL) remains largely sample-inefficient. The most common RL algorithms rely on random action sampling to discover new strategies, resulting in agents that allocate most of their training budget to motions in free space, away from the contacts from which manipulation skills emerge.
초록에서 가져왔습니다. 요약을 준비 중입니다.