Efficient and Safe Exploration in Deterministic Markov Decision Processes with Unknown Transition Models
Efficient and Safe Exploration in Deterministic Markov Decision Processes with Unknown Transition Models
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.