- document
-
Jarne Ornia, D. (author), Mazo, M. (author)We present an approach to safely reduce the communication required between agents in a Multi-Agent Reinforcement Learning system by exploiting the inherent robustness of the underlying Markov Decision Process. We compute robustness certificate functions (off-line), that give agents a conservative indication of how far their state measurements...conference paper 2022
- document
-
Jarne Ornia, D. (author), Mazo, M. (author)We present an approach to reduce the communication of information needed on a Distributed Q-Learning system inspired by Event Triggered Control (ETC) techniques. We consider a baseline scenario of a Distributed Q-Learning problem on a Markov Decision Process (MDP). Following an event-based approach, N agents sharing a value function explore the...conference paper 2022
- document
-
Verdier, C.F. (author), Babuska, R. (author), Shyrokau, B. (author), Mazo, M. (author)Control systems designed via learning methods, aiming at quasi-optimal solutions, typically lack stability and performance guarantees. We propose a method to construct a near-optimal control law by means of model-based reinforcement learning and subsequently verifying the reachability and safety of the closed-loop control system through an...journal article 2019