Search Results for author:
Found 9 papers, 2 papers with code
Learning Environment Models with Continuous Stochastic Dynamics
We aim to provide insights into the decisions faced by the agent by learning an automaton model of environmental behavior under the control of an agent.
On the Relationship Between RNN Hidden State Vectors and Semantic Ground Truth
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 hypothesis.
Online Shielding for Reinforcement Learning
The intuition behind online shielding is to compute at runtime the set of all states that could be reached in the near future.
Automata Learning meets Shielding
Iteratively, we use the collected data to learn new MDPs with higher accuracy, resulting in turn in shields able to prevent more safety violations.
Reinforcement Learning under Partial Observability Guided by Learned Environment Models
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 precise interaction with its environment.
Search-Based Testing of Reinforcement Learning
We present a search-based testing framework that enables a wide range of novel analysis capabilities for evaluating the safety and performance of deep RL agents.
Online Shielding for Stochastic Systems
The intuition behind online shielding is to compute during run-time the set of all states that could be reached in the near future.
Logic in Computer Science
Learning a Behavior Model of Hybrid Systems Through Combining Model-Based Testing and Machine Learning (Full Version)
Therefore, there is considerable interest in learning such hybrid behavior by means of machine learning which requires sufficient and representative training data covering the behavior of the physical system adequately.
L*-Based Learning of Markov Decision Processes (Extended Version)
In this work, we study L*-based learning of deterministic Markov decision processes, first assuming an ideal setting with perfect information.
