3 papers
cs.AI2019
Counterexample-Guided Strategy Improvement for POMDPs Using Recurrent Neural Networks
Steven Carr, Nils Jansen, Ralf Wimmer +3
We study strategy synthesis for partially observable Markov decision processes (POMDPs). The particular problem is to determine strategies that provably adhere to (probabilistic) t…
math.OC2018
Affine Multiplexing Networks: System Analysis, Learning, and Computation
Ivan Papusha, Ufuk Topcu, Steven Carr +1
We introduce a novel architecture and computational framework for formal, automated analysis of systems with a broad set of nonlinearities in the feedback loop, such as neural netw…
cs.AI2018
Human-in-the-Loop Synthesis for Partially Observable Markov Decision Processes
Steven Carr, Nils Jansen, Ralf Wimmer +2
We study planning problems where autonomous agents operate inside environments that are subject to uncertainties and not fully observable. Partially observable Markov decision proc…