Alert button
Picture for Ralf Wimmer

Ralf Wimmer

Alert button

Strengthening Deterministic Policies for POMDPs

Jul 16, 2020
Leonore Winterer, Ralf Wimmer, Nils Jansen, Bernd Becker

Figure 1 for Strengthening Deterministic Policies for POMDPs
Figure 2 for Strengthening Deterministic Policies for POMDPs
Figure 3 for Strengthening Deterministic Policies for POMDPs
Figure 4 for Strengthening Deterministic Policies for POMDPs
Viaarxiv icon

Counterexample-Guided Strategy Improvement for POMDPs Using Recurrent Neural Networks

Mar 21, 2019
Steven Carr, Nils Jansen, Ralf Wimmer, Alexandru C. Serban, Bernd Becker, Ufuk Topcu

Figure 1 for Counterexample-Guided Strategy Improvement for POMDPs Using Recurrent Neural Networks
Figure 2 for Counterexample-Guided Strategy Improvement for POMDPs Using Recurrent Neural Networks
Figure 3 for Counterexample-Guided Strategy Improvement for POMDPs Using Recurrent Neural Networks
Figure 4 for Counterexample-Guided Strategy Improvement for POMDPs Using Recurrent Neural Networks
Viaarxiv icon

Human-in-the-Loop Synthesis for Partially Observable Markov Decision Processes

Feb 27, 2018
Steven Carr, Nils Jansen, Ralf Wimmer, Jie Fu, Ufuk Topcu

Figure 1 for Human-in-the-Loop Synthesis for Partially Observable Markov Decision Processes
Figure 2 for Human-in-the-Loop Synthesis for Partially Observable Markov Decision Processes
Figure 3 for Human-in-the-Loop Synthesis for Partially Observable Markov Decision Processes
Figure 4 for Human-in-the-Loop Synthesis for Partially Observable Markov Decision Processes
Viaarxiv icon

Motion Planning under Partial Observability using Game-Based Abstraction

Aug 14, 2017
Leonore Winterer, Sebastian Junges, Ralf Wimmer, Nils Jansen, Ufuk Topcu, Joost-Pieter Katoen, Bernd Becker

Figure 1 for Motion Planning under Partial Observability using Game-Based Abstraction
Figure 2 for Motion Planning under Partial Observability using Game-Based Abstraction
Viaarxiv icon