119 citations · 136 across the 14 of their papers we have counts for
11 papers · 1 filter
ORCAID: Oblique Rule-Based Continuous-Action Interpretation for Deep RL Policies
Ignacio D. Lopez-Miguel, Ezio Bartocci, Thomas Eiter +1
Explainability remains a key issue in reinforcement learning (RL). Distilling an interpretable policy from an agent trained in a complex environment is particularly challenging whe…
Rule-Guided Reinforcement Learning Policy Evaluation and Improvement
Martin Tappler, Ignacio D. Lopez-Miguel, Sebastian Tschiatschek +1
We consider the challenging problem of using domain knowledge to improve deep reinforcement learning policies. To this end, we propose LEGIBLE, a novel approach, following a multi-…
Test Where Decisions Matter: Importance-driven Testing for Deep Reinforcement Learning
Stefan Pranger, Hana Chockler, Martin Tappler +1
In many Deep Reinforcement Learning (RL) problems, decisions in a trained policy vary in significance for the expected safety and performance of the policy. Since RL policies are v…
Learning Environment Models with Continuous Stochastic Dynamics
Martin Tappler, Edi Muškardin, Bernhard K. Aichernig +1
Solving control tasks in complex environments automatically through learning offers great potential. While contemporary techniques from deep reinforcement learning (DRL) provide ef…
On the Relationship Between RNN Hidden State Vectors and Semantic Ground Truth
Edi Muškardin, Martin Tappler, Ingo Pill +2
We examine the assumption that the hidden-state vectors of recurrent neural networks (RNNs) tend to form clusters of semantically similar vectors, which we dub the clustering hypot…
Online Shielding for Reinforcement Learning
Bettina Könighofer, Julian Rudolf, Alexander Palmisano +2
Besides the recent impressive results on reinforcement learning (RL), safety is still one of the major research challenges in RL. RL is a machine-learning approach to determine nea…
Automata Learning meets Shielding
Martin Tappler, Stefan Pranger, Bettina Könighofer +3
Safety is still one of the major research challenges in reinforcement learning (RL). In this paper, we address the problem of how to avoid safety violations of RL agents during exp…
Reinforcement Learning under Partial Observability Guided by Learned Environment Models
Edi Muskardin, Martin Tappler, Bernhard K. Aichernig +1
In practical applications, we can rarely assume full observability of a system's environment, despite such knowledge being important for determining a reactive control system's pre…
Search-Based Testing of Reinforcement Learning
Martin Tappler, Filip Cano Córdoba, Bernhard K. Aichernig +1
Evaluation of deep reinforcement learning (RL) is inherently challenging. Especially the opaqueness of learned policies and the stochastic nature of both agents and environments ma…
Learning a Behavior Model of Hybrid Systems Through Combining Model-Based Testing and Machine Learning (Full Version)
Bernhard K. Aichernig, Roderick Bloem, Masoud Ebrahimi +6
Models play an essential role in the design process of cyber-physical systems. They form the basis for simulation and analysis and help in identifying design problems as early as p…
L*-Based Learning of Markov Decision Processes (Extended Version)
Martin Tappler, Bernhard K. Aichernig, Giovanni Bacci +2
Automata learning techniques automatically generate system models from test observations. These techniques usually fall into two categories: passive and active. Passive learning us…