予測力から方策学習可能性へ:動画生成モデルの事前知識を活用するZERITH V2.5
ZERITH V2.5: From Predictive Power to Policy Learnability
動画生成モデルの中間特徴を行動方策が読み取るvideo-actionモデルを提案し、予測学習の監督方法が後続の行動学習に与える影響を実験的に分析した。
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: Chenxi Han, Ruby, Epoch, Orion, Luke, Bin, Dusk, Lyra, Cal, Alvin, Hubert, Alex, Jiahe Han, Tao Zhang, Hang Liu, Shoujie Li, Yizhe Li, Bokui Chen, Houde Liu, Guoping Pan, Yi Cheng
分類: cs.RO
原文アブストラクト
When humans learn to manipulate an unfamiliar object, they may already be able to anticipate how its state will change while still being unable to control it skillfully. This gap between prediction and control motivates us to study how the priors acquired by video generation models can be used effectively by an action policy. We present ZERITH V2.5, a video-action model (VAM) in which the action policy reads intermediate features of a video generation model, and use it to study, under fixed demonstrations and a fixed total number of updates, what kind of predictive training improves subsequent action learning. We find that the way video predictive training is supervised affects subsequent action learning. In our experiments, adapting at many noise levels yields a large gain, while adapting only at the noise level used at deployment yields none. Weight-transfer experiments further show that the gain stays with the adapted weights when they remain in the video generation model and disappears when they are used only to initialize the action policy. Initial loss and gradient measurements at the start of joint training indicate that target-domain predictive training gives the video model a better starting state, making subsequent joint learning of prediction and action easier. Under matched data and training budgets, predictive adaptation improves control. We evaluate the complete policy on LIBERO, LIBERO-Plus, Meta-World MT50, and real-robot tasks.
