未知の遷移モデルを持つ決定論的MDPにおける効率的で安全な探索
Efficient and Safe Exploration in Deterministic Markov Decision Processes with Unknown Transition Models
リプシッツ連続性を利用して探索中に危険状態へ遷移しないことを決定論的に保証しつつ、安全領域の探索に必要な行動数を削減するアルゴリズムを提案し、ナビゲーションタスクのシミュレーションで有効性を示した論文。
著者: Erdem Bıyık, Jonathan Margoliash, Shahrouz Ryan Alimo, Dorsa Sadigh
分類: cs.RO, cs.AI, cs.LG, cs.SY, eess.SY
原文アブストラクト
We propose a safe exploration algorithm for deterministic Markov Decision Processes with unknown transition models. Our algorithm guarantees safety by leveraging Lipschitz-continuity to ensure that no unsafe states are visited during exploration. Unlike many other existing techniques, the provided safety guarantee is deterministic. Our algorithm is optimized to reduce the number of actions needed for exploring the safe space. We demonstrate the performance of our algorithm in comparison with baseline methods in simulation on navigation tasks.
