新規性検出による世界モデルの分布シフト抑制
Bounding Distributional Shifts in World Modeling through Novelty Detection
変分オートエンコーダを新規性検出器として用い、モデルベース計画中に学習済み世界モデルが訓練データ分布から逸脱するのを防ぐ手法を提案し、DINO-WMに組み込んでデータ効率の向上を示した。
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: Eric Jing, Abdeslam Boularias
分類: cs.RO, cs.AI
原文アブストラクト
Recent work on visual world models shows significant promise in latent state dynamics obtained from pre-trained image backbones. However, most of the current approaches are sensitive to training quality, requiring near-complete coverage of the action and state space during training to prevent divergence during inference. To make a model-based planning algorithm more robust to the quality of the learned world model, we propose in this work to use a variational autoencoder as a novelty detector to ensure that proposed action trajectories during planning do not cause the learned model to deviate from the training data distribution. To evaluate the effectiveness of this approach, a series of experiments in challenging simulated robot environments was carried out, with the proposed method incorporated into a model-predictive control policy loop extending the DINO-WM architecture. The results clearly show that the proposed method improves over state-of-the-art solutions in terms of data efficiency.
