no code implementations • 18 Dec 2023 • Rohan Mitta, Hosein Hasanbeig, Jun Wang, Daniel Kroening, Yiannis Kantaros, Alessandro Abate
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 learning.
no code implementations • 23 Nov 2023 • David A. Kelly, Hana Chockler, Daniel Kroening, Nathan Blake, Aditi Ramaswamy, Melane Navaratnarajah, Aaditya Shivakumar
In this paper, we propose a new black-box explainability algorithm and tool, YO-ReX, for efficient explanation of the outputs of object detectors.
no code implementations • 25 Sep 2023 • Hana Chockler, David A. Kelly, Daniel Kroening
Existing explanation tools for image classifiers usually give only a single explanation for an image's classification.
1 code implementation • 21 Sep 2022 • 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 linear temporal specification with maximal probability.
no code implementations • 1 Jun 2021 • Isaac Dunn, Hadrien Pouget, Daniel Kroening, Tom Melham
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 the desired DNN output is known.
no code implementations • ICCV 2021 • 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.
no code implementations • 7 Feb 2021 • 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.
1 code implementation • 20 Jan 2021 • Mirco Giacobbe, Mohammadhosein Hasanbeig, Daniel Kroening, Hjalmar Wijk
We present the first exact method for analysing and ensuring the safety of DRL agents for Atari games.
2 code implementations • NeurIPS 2021 • Hadrien Pouget, Hana Chockler, Youcheng Sun, Daniel Kroening
Policies trained via Reinforcement Learning (RL) are often needlessly complex, making them difficult to analyse and interpret.
no code implementations • 26 Feb 2020 • Mohammadhosein Hasanbeig, Alessandro Abate, Daniel Kroening
This paper presents the concept of an adaptive safe padding that forces Reinforcement Learning (RL) to synthesise optimal control policies while ensuring safety during the learning process.
no code implementations • 29 Jan 2020 • Isaac Dunn, Laura Hanu, Hadrien Pouget, Daniel Kroening, Tom Melham
We cannot guarantee that training datasets are representative of the distribution of inputs that will be encountered during deployment.
no code implementations • 25 Jan 2020 • Elizabeth Polgreen, Ralph Abboud, Daniel Kroening
Program synthesis is the generation of a program from a specification.
1 code implementation • 15 Jan 2020 • Natasha Yogananda Jeppu, Tom Melham, Daniel Kroening, John O'Leary
Abstract models of system-level behaviour have applications in design exploration, analysis, testing and verification.
Formal Languages and Automata Theory Software Engineering
1 code implementation • 22 Nov 2019 • Mohammadhosein Hasanbeig, Natasha Yogananda Jeppu, Alessandro Abate, Tom Melham, Daniel Kroening
This paper proposes DeepSynth, a method for effective training of deep Reinforcement Learning (RL) agents when the reward is sparse and non-Markovian, but at the same time progress towards the reward requires achieving an unknown sequence of high-level objectives.
2 code implementations • 23 Sep 2019 • Lim Zun Yuan, Mohammadhosein Hasanbeig, Alessandro Abate, Daniel Kroening
We propose an actor-critic, model-free, and online Reinforcement Learning (RL) framework for continuous-state continuous-action Markov Decision Processes (MDPs) when the reward is highly sparse but encompasses a high-level temporal structure.
1 code implementation • 11 Sep 2019 • Mohammadhosein Hasanbeig, Yiannis Kantaros, Alessandro Abate, Daniel Kroening, George J. Pappas, Insup Lee
Reinforcement Learning (RL) has emerged as an efficient method of choice for solving complex sequential decision making problems in automatic control, computer science, economics, and biology.
1 code implementation • 6 Aug 2019 • Youcheng Sun, Hana Chockler, Xiaowei Huang, Daniel Kroening
The black-box nature of deep neural networks (DNNs) makes it impossible to understand why a particular output is produced, creating demand for "Explainable AI".
no code implementations • 7 May 2019 • Isaac Dunn, Hadrien Pouget, Tom Melham, Daniel Kroening
Neural networks are vulnerable to adversarially-constructed perturbations of their inputs.
1 code implementation • 2 Feb 2019 • Hosein Hasanbeig, Daniel Kroening, Alessandro Abate
Reinforcement Learning (RL) is a widely employed machine learning architecture that has been applied to a variety of control problems.
no code implementations • 18 Dec 2018 • Xiaowei Huang, Daniel Kroening, Wenjie Ruan, James Sharp, Youcheng Sun, Emese Thamo, Min Wu, Xinping Yi
In the past few years, significant progress has been made on deep neural networks (DNNs) in achieving human-level performance on several long-standing tasks.
no code implementations • 20 Sep 2018 • Mohammadhosein Hasanbeig, Alessandro Abate, Daniel Kroening
We propose a method for efficient training of Q-functions for continuous-state Markov Decision Processes (MDPs) such that the traces of the resulting policies satisfy a given Linear Temporal Logic (LTL) property.
2 code implementations • 30 Apr 2018 • Youcheng Sun, Min Wu, Wenjie Ruan, Xiaowei Huang, Marta Kwiatkowska, Daniel Kroening
Concolic testing combines program execution and symbolic analysis to explore the execution paths of a software program.
1 code implementation • 23 Apr 2018 • Sean Heelan, Tom Melham, Daniel Kroening
In this paper we present the first automatic approach to the problem, based on pseudo-random black-box search.
Cryptography and Security Programming Languages
2 code implementations • 16 Apr 2018 • Wenjie Ruan, Min Wu, Youcheng Sun, Xiaowei Huang, Daniel Kroening, Marta Kwiatkowska
In this paper we focus on the $L_0$ norm and aim to compute, for a trained DNN and an input, the maximal radius of a safe norm ball around the input within which there are no adversarial examples.
no code implementations • 10 Mar 2018 • Youcheng Sun, Xiaowei Huang, Daniel Kroening, James Sharp, Matthew Hill, Rob Ashmore
In this paper, inspired by the MC/DC coverage criterion, we propose a family of four novel test criteria that are tailored to structural features of DNNs and their semantics.
1 code implementation • 24 Jan 2018 • Mohammadhosein Hasanbeig, Alessandro Abate, Daniel Kroening
With this reward function, the policy synthesis procedure is "constrained" by the given specification.
2 code implementations • 3 Jul 2015 • César Rodríguez, Marcelo Sousa, Subodh Sharma, Daniel Kroening
Over benchmarks with busy-waits, among others, our experiments show a dramatic reduction in the number of executions when compared to a state-of-the-art DPOR.
Logic in Computer Science Programming Languages D.2.4