模倣学習における実行不可能な最適化問題と階層的拡張ラグランジュ法
Infeasible optimization problems and the hierarchical augmented Lagrangian method in imitation learning
模倣学習の制約付き最適化問題が実行不可能になる場合に、拡張ラグランジュ法を用いて最も近い実行可能な解へ収束させる手法を提案し、運転シミュレーションで実証した。
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: Roland Andrews, Justin Carpentier, Ajay Sathya
分類: cs.RO
原文アブストラクト
Imitation learning (IL) is an effective approach to train complex robotics policies. Recent works have introduced hard constraints into imitation-learning optimization problems to ensure safety, stability, and robustness of the learned policy. However, we argue that these constraints are sometimes infeasible, which can lead to unstable or difficult training dynamics. We study a simple remedy for such situations based on recent theoretical results on the augmented Lagrangian method in infeasible settings. We show that our approach drives the learned policy toward the solution of a closest-feasible constrained IL problem with desirable properties. The method is illustrated on a toy driving example with a total-acceleration constraint and pedestrian-safety constraints, a setting in which infeasibility can naturally arise while still allowing a safe learned policy.
