173 citations · 655 across the 66 of their papers we have counts for
18 papers · 1 filter
Safeguarded Progress in Reinforcement Learning: Safe Bayesian Exploration for Control Policy Synthesis
Rohan Mitta, Hosein Hasanbeig, Jun Wang +3
This paper addresses the problem of maintaining safety during training in Reinforcement Learning (RL), such that the safety constraint violations are bounded at any point during le…
LCRL: Certified Policy Synthesis via Logically-Constrained Reinforcement Learning
Hosein Hasanbeig, Daniel Kroening, Alessandro Abate
LCRL is a software tool that implements model-free Reinforcement Learning (RL) algorithms over unknown Markov Decision Processes (MDPs), synthesising policies that satisfy a given…
Exposing Previously Undetectable Faults in Deep Neural Networks
Isaac Dunn, Hadrien Pouget, Daniel Kroening +1
Existing methods for testing DNNs solve the oracle problem by constraining the raw features (e.g. image pixel values) to be within a small distance of a dataset example for which t…
Explanations for Occluded Images
Hana Chockler, Daniel Kroening, Youcheng Sun
Existing algorithms for explaining the output of image classifiers perform poorly on inputs where the object of interest is partially occluded. We present a novel, black-box algori…
Neural Termination Analysis
Mirco Giacobbe, Daniel Kroening, Julian Parsert
We introduce a novel approach to the automated termination analysis of computer programs: we use neural networks to represent ranking functions. Ranking functions map program state…
Ranking Policy Decisions
Hadrien Pouget, Hana Chockler, Youcheng Sun +1
Policies trained via Reinforcement Learning (RL) are often needlessly complex, making them difficult to analyse and interpret. In a run with time steps, a policy will make …