表形式基盤モデルを訓練不要のワールドモデルとして評価する
An Evaluation of Tabular Foundation Models as Training-Free World Models
事前学習済みの表形式基盤モデル(TabFM)を、遷移ペアに対する文脈内回帰として次状態予測に用い、訓練不要のダイナミクスモデルとしてどこで有効でどこで破綻するかを合成力学系とロボット歩行ベンチマークで検証した。
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: Xian Yeow Lee, Ryoichi Takase, Ahmed Farahat
分類: cs.LG, cs.AI
原文アブストラクト
World models are widely considered to be a potential key component of model-based reinforcement learning and robot planning, but typically require task-specific training on substantial interaction data. We investigate whether a pretrained tabular foundation model (TabFM) can serve as a training-free dynamics model for world modeling by framing next-state prediction as in-context regression over transition pairs, and where such a model helps and where it breaks. Across synthetic dynamical systems and robot locomotion benchmarks, TabFM is more accurate than LSTM and MLP models trained from scratch on the same limited transitions in almost all settings, and among regressors fitted to the same data it is the most accurate on locomotion, while a Gaussian process is more accurate on smooth low-dimensional systems. However, models trained on the full dataset remain substantially better on most systems. When rolled out autoregressively over multiple steps, TabFM's accuracy depends strongly on how much context it is given. With a short context, its rollouts quickly degrade to the level of a trivial baseline, whereas with a long context they improve substantially and, on one locomotion task, exceed a trained LSTM. Inference is also about three orders of magnitude slower than an LSTM. Overall, in their current state, we find that training-free priors are useful as predictors when data are scarce and enough context is available, but they are not yet a substitute for trained world models in planning.