Search Results for author:
Found 18 papers, 7 papers with code
Human vs. Machine: Language Models and Wargames
Wargames have a long history in the development of military strategy and the response of nations to threats or attacks.
Constrained Hierarchical Monte Carlo Belief-State Planning
Optimal plans in Constrained Partially Observable Markov Decision Processes (CPOMDPs) maximize reward objectives while satisfying hard cost constraints, generalizing safe planning under state and transition uncertainty.
Transcending the Attention Paradigm: Representation Learning from Geospatial Social Media Data
While transformers have pioneered attention-driven architectures as a cornerstone of language modeling, their dependence on explicitly contextual information underscores limitations in their abilities to tacitly learn overarching textual themes.
A Holistic Assessment of the Reliability of Machine Learning Systems
As machine learning (ML) systems increasingly permeate high-stakes settings such as healthcare, transportation, military, and national security, concerns regarding their reliability have emerged.
Reflections from the Workshop on AI-Assisted Decision Making for Conservation
In this white paper, we synthesize key points made during presentations and discussions from the AI-Assisted Decision Making for Conservation workshop, hosted by the Center for Research on Computation and Society at Harvard University on October 20-21, 2022.
BetaZero: Belief-State Planning for Long-Horizon POMDPs using Learned Approximations
BetaZero learns offline approximations that replace heuristics to enable online decision making in long-horizon problems.
Model-based Validation as Probabilistic Inference
Estimating the distribution over failures is a key step in validating autonomous systems.
Leveraging Compositional Methods for Modeling and Verification of an Autonomous Taxi System
We apply a compositional formal modeling and verification method to an autonomous aircraft taxi system.
Online Planning for Constrained POMDPs with Continuous Spaces through Dual Ascent
Rather than augmenting rewards with penalties for undesired behavior, Constrained Partially Observable Markov Decision Processes (CPOMDPs) plan safely by imposing inviolable hard constraint value budgets.
A Deep Reinforcement Learning Approach to Rare Event Estimation
An important step in the design of autonomous systems is to evaluate the probability that a failure will occur.
A POMDP Model for Safe Geological Carbon Sequestration
This POMDP model can be used as a test bed to drive the development of novel decision-making algorithms for CCS operations.
Verifying Inverse Model Neural Networks
When the forward model that produced the observations is nonlinear and stochastic, solving the inverse problem is very challenging.
Transfer Learning for Efficient Iterative Safety Validation
Safety validation is important during the development of safety-critical autonomous systems but can require significant computational effort.
A Survey of Algorithms for Black-Box Safety Validation of Cyber-Physical Systems
Autonomous cyber-physical systems (CPS) can improve safety and efficiency for safety-critical applications, but require rigorous testing before deployment.
Scalable Autonomous Vehicle Safety Validation through Dynamic Programming and Scene Decomposition
In this work, we present a new safety validation approach that attempts to estimate the distribution over failures of an autonomous policy using approximate dynamic programming.
Interpretable Safety Validation for Autonomous Vehicles
Our methodology is demonstrated for the safety validation of an autonomous vehicle in the context of an unprotected left turn and a crosswalk with a pedestrian.
The Adaptive Stress Testing Formulation
Validation is a key challenge in the search for safe autonomy.
Adaptive Stress Testing with Reward Augmentation for Autonomous Vehicle Validation
Determining possible failure scenarios is a critical step in the evaluation of autonomous vehicle systems.
