Related papers: Programming and Reasoning with Partial Observabili…

Reinforcement learning in partially observable environments is typically challenging, as it requires agents to learn an estimate of the underlying system state. These challenges are exacerbated in multi-agent settings, where agents learn…

This work introduces a novel deep learning-based architecture, termed the Deep Belief Markov Model (DBMM), which provides efficient, model-formulation agnostic inference in Partially Observable Markov Decision Process (POMDP) problems. The…

Although a recent shift has been made in the field of predictive process monitoring to use models from the explainable artificial intelligence field, the evaluation still occurs mainly through performance-based metrics, thus not accounting…

Reinforcement learning agents deployed in the real world often have to cope with partially observable environments. Therefore, most agents employ memory mechanisms to approximate the state of the environment. Recently, there have been…

Using LLMs not to predict plans but to formalize an environment into the Planning Domain Definition Language (PDDL) has been shown to improve performance and control. While most existing methodology only applies to fully observable…

We introduce games with probabilistic uncertainty, a natural model for controller synthesis in which the controller observes the state of the system through imprecise sensors that provide correct information about the current state with a…

Security-sensitive applications that execute untrusted code often check the code's integrity by comparing its syntax to a known good value or sandbox the code to contain its effects. System M is a new program logic for reasoning about such…

Machine language acquisition is often presented as a problem of imitation learning: there exists a community of language users from which a learner observes speech acts and attempts to decode the mappings between utterances and situations.…

In the past few years LLMs have emerged as a tool that can aid programmers by taking natural language descriptions and generating code based on it. However, the reliability of LLM code generation and current validation techniques for it are…

Safety-critical cyber-physical systems require control strategies whose worst-case performance is robust against adversarial disturbances and modeling uncertainties. In this paper, we present a framework for approximate control and learning…

Interpretable Machine Learning faces a recurring challenge of explaining the predictions made by opaque classifiers such as ensemble models, kernel methods, or neural networks in terms that are understandable to humans. When the model is…

LTLf synthesis under partial observability requires reasoning about unobservable environment variables, which is typically handled by constructing a belief-state DFA via subset construction that universally quantifies these variables.…

We describe the integration of logical and uncertain reasoning methods to identify the likely source and location of software problems. To date, software engineers have had few tools for identifying the sources of error in complex software…

A program's exceptional behavior can substantially complicate its control flow, and hence accurately reasoning about the program's correctness. On the other hand, formally verifying realistic programs is likely to involve exceptions -- a…

Decision processes with incomplete state feedback have been traditionally modeled as Partially Observable Markov Decision Processes. In this paper, we present an alternative formulation based on probabilistic regular languages. The proposed…

We consider the problem of imitation learning from expert demonstrations in partially observable Markov decision processes (POMDPs). Belief representations, which characterize the distribution over the latent states in a POMDP, have been…

In order for an autonomous robot to efficiently explore an unknown environment, it must account for uncertainty in sensor measurements, hazard assessment, localization, and motion execution. Making decisions for maximal reward in a…

As large language models (LLMs) continue to demonstrate remarkable abilities across various domains, computer scientists are developing methods to understand their cognitive processes, particularly concerning how (and if) LLMs internally…

The problem of belief tracking in the presence of stochastic actions and observations is pervasive and yet computationally intractable. In this work we show however that probabilistic beliefs can be maintained in factored form exactly and…

Probabilistic programming provides a convenient lingua franca for writing succinct and rigorous descriptions of probabilistic models and inference tasks. Several probabilistic programming languages, including Anglican, Church or Hakaru,…