papers AI Learner
The Github is limit! Click to go to the new site.

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

2019-04-01
Erdem Bıyık, Jonathan Margoliash, Shahrouz Ryan Alimo, Dorsa Sadigh

Abstract

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.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1904.01068

PDF

http://arxiv.org/pdf/1904.01068


Similar Posts

Comments