過ぎたるは及ばざるが如し：sim2realの努力が政策学習を妨げるとき（そしてその対処法）
Too Much of a Good Thing: When sim2real Efforts Impede Policy Learning (And What to Do About It)
sim2realの努力が政策学習と不整合を起こし、シミュレータへの過度な依存や探索の制限を招く問題を指摘し、ロボットの運動学のみを設計制約とするsim2sim2realパラダイムを提案する論文。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Kyle Morgenstein, Bharath Masetty, Stephen Welch, Luis Sentis
分類: cs.RO, cs.AI
原文アブストラクト
While sim2real efforts are necessary for effective policy transfer to hardware, there is such a thing as too much of a good thing. We argue that sim2real efforts have led to misaligned incentives with policy learning, resulting in simulator lock in and poor policy exploration due to the unreasonable constraints imposed by the real world. We offer a diagnosis and explanation of the current status of the problem, and propose a potential solution via a sim2sim2real paradigm that leverages the robot's kinematics as the sole design constraint.
