-A A +A

Alessandro Abate is an Invited Speaker @ First Workshop on Artificial Intelligence and fOrmal VERification, Logic, Automata, and sYnthesis OVERLAY @ AIxIA 2019 November 19-20 2019, Rende (Italy)


First Workshop on Artificial Intelligence and fOrmal VERification, Logic, Automata, and sYnthesis OVERLAY @ AIxIA 2019 November 19-20 2019, Rende (Italy)

https://overlay.uniud.it/workshop/2019/

 

Invited speaker:Alessandro Abate (Oxford University)

Title: Certified Reinforcement Learning with Logic Guidance

A model-free Reinforcement Learning (RL) framework is proposed, to synthesise policies for an unknown, and possibly continuous-state, Markov Decision Process (MDP), such that a given linear temporal property is satisfied.

We convert the given property into an automaton, namely a finite-state machine expressing the property. Exploiting the structure of the automaton, we shape an adaptive reward function on-the-fly, so that the RL algorithm can synthesise a policy resulting in traces that probabilistically satisfy the linear temporal property.

Under the assumption that the MDP has finite number of states, theoretical guarantees are provided on the convergence of the RL algorithm. Whenever the MDP has a continuous state space, we empirically show that our framework finds satisfying policies, if existing. Additionally, the proposed algorithm can handle time-varying periodic environments.

The performance of the proposed architecture is evaluated via a set of numerical examples and benchmarks, where we observe an improvement of one order of magnitude in the number of iterations required for the policy synthesis, compared to existing approaches (when available).

Speaker's bio

Alessandro Abate is Professor of Verification and Control in the Department of Computer Science at the University of Oxford (UK), and is a fellow of the Alan Turing Institute in London (UK). He received a Laurea in Electrical Engineering in October 2002 from the University of Padova (IT), an MS in May 2004 and a PhD in December 2007, both in Electrical Engineering and Computer Sciences, at UC Berkeley (USA). He has been an International Fellow in the CS Lab at SRI International in Menlo Park (USA), and a PostDoctoral Researcher at Stanford University (USA), in the Department of Aeronautics and Astronautics. From June 2009 to mid 2013 he has been an Assistant Professor at the Delft Centre for Systems and Control, TU Delft - Delft University of Technology (NL).

CONTACT US

Oxford Control and Verification (OXCAV) Group

C/O Department of Computer Science

Wolfson Building, Parks Rd, Oxford OX1 3QD

T: +44 (0) 18656 10767

Education - This is a contributing Drupal Theme
Design by WeebPal.