Search Results for author:
Found 10 papers, 4 papers with code
Manipulating Neural Path Planners via Slight Perturbations
In this paper, we propose a novel approach to specify and inject a range of hidden malicious behaviors, known as backdoors, into neural path planners.
Co-learning Planning and Control Policies Constrained by Differentiable Logic Specifications
Synthesizing planning and control policies in robotics is a fundamental task, further complicated by factors such as complex logic specifications and high-dimensional robot dynamics.
Hierarchical Reinforcement Learning
reinforcement-learning
+2
DistSPECTRL: Distributing Specifications in Multi-Agent Reinforcement Learning Systems
While notable progress has been made in specifying and learning objectives for general cyber-physical systems, applying these methods to distributed multi-agent systems still pose significant challenges.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Defending Observation Attacks in Deep Reinforcement Learning via Detection and Denoising
We focus our attention on well-trained deterministic and stochastic neural network policies in the context of continuous control benchmarks subject to four well-studied observation space adversarial attacks.
Model-free Neural Lyapunov Control for Safe Robot Navigation
Model-free Deep Reinforcement Learning (DRL) controllers have demonstrated promising results on various challenging non-linear control tasks.
Scalable Synthesis of Verified Controllers in Deep Reinforcement Learning
There has been significant recent interest in devising verification techniques for learning-enabled controllers (LECs) that manage safety-critical systems.
Repairing Serializability Bugs in Distributed Database Programs via Automated Schema Refactoring
Serializability is a well-understood concurrency control mechanism that eases reasoning about highly-concurrent database programs.
Programming Languages
Robustness to Adversarial Attacks in Learning-Enabled Controllers
We consider shield-based defenses as a means to improve controller robustness in the face of such perturbations.
ART: Abstraction Refinement-Guided Training for Provably Correct Neural Networks
Our key insight is that we can integrate an optimization-based abstraction refinement loop into the learning process and operate over dynamically constructed partitions of the input space that considers accuracy and safety objectives synergistically.
An Inductive Synthesis Framework for Verifiable Reinforcement Learning
Rather than enforcing safety by examining and altering the structure of a complex neural network implementation, our technique uses blackbox methods to synthesizes deterministic programs, simpler, more interpretable, approximations of the network that can nonetheless guarantee desired safety properties are preserved, even when the network is deployed in unanticipated or previously unobserved environments.
