Search Results for author:
Found 10 papers, 1 papers with code
Analyzing Adversarial Inputs in Deep Reinforcement Learning
In recent years, Deep Reinforcement Learning (DRL) has become a popular paradigm in machine learning due to its successful applications to real-world and complex systems.
Enumerating Safe Regions in Deep Neural Networks with Provable Probabilistic Guarantees
Identifying safe areas is a key point to guarantee trust for systems that are based on Deep Neural Networks (DNNs).
Formally Explaining Neural Networks within Reactive Systems
We evaluate our approach on two popular benchmarks from the domain of automated navigation; and observe that our methods allow the efficient computation of minimal and minimum explanations, significantly outperforming the state of the art.
The #DNN-Verification Problem: Counting Unsafe Inputs for Deep Neural Networks
Due to the #P-completeness of the problem, we also propose a randomized, approximate method that provides a provable probabilistic bound of the correct count while significantly reducing computational requirements.
Constrained Reinforcement Learning for Robotics via Scenario-Based Programming
Deep reinforcement learning (DRL) has achieved groundbreaking successes in a wide variety of robotic applications.
Verifying Learning-Based Robotic Navigation Systems
Our work is the first to establish the usefulness of DNN verification in identifying and filtering out suboptimal DRL policies in real-world robots, and we believe that the methods presented here are applicable to a wide range of systems that incorporate deep-learning-based agents.
Curriculum Learning for Safe Mapless Navigation
To this end, we present a CL approach that leverages Transfer of Learning (ToL) and fine-tuning in a Unity-based simulation with the Robotnik Kairos as a robotic agent.
Benchmarking Safe Deep Reinforcement Learning in Aquatic Navigation
Aquatic navigation is an extremely challenging task due to the non-stationary environment and the uncertainties of the robotic platform, hence it is crucial to consider the safety aspect of the problem, by analyzing the behavior of the trained network to avoid dangerous situations (e. g., collisions).
Genetic Soft Updates for Policy Evolution in Deep Reinforcement Learning
The combination of Evolutionary Strategies (ES) and Deep Reinforcement Learning (DRL) has been recently proposed to merge the benefits of both solutions.
Evaluating the Safety of Deep Reinforcement Learning Models using Semi-Formal Verification
In this paper, we present a semi-formal verification approach for decision-making tasks, based on interval analysis, that addresses the computational demanding of previous verification frameworks and design metrics to measure the safety of the models.
