12 accepted papers
Prompt optimization methods have demonstrated significant effectiveness in aligning black-box large language models (LLMs). In parallel, inference scaling strategies such as Best-of-N Sampling and Majority Voting have likewise been shown to improve alignment and performance by trading additional com
Many real-world applications require decision-making where the environmental dynamics evolve over time. These non-stationary environments pose significant challenges to traditional decision-making models, which typically assume stationary dynamics. Non-stationary Markov decision processes (NS-MDPs)…
Partially Observable Markov Decision Processes (POMDPs) provide a structured framework for decision-making under uncertainty, but their application requires efficient belief updates. Sequential Importance Resampling Particle Filters (SIRPF), also known as Bootstrap Particle Filters, are commonly use
Robots deployed in the real world over extendedperiods of time need to reason about unexpected failures, learn to predict them, and to proactively take actions to avoid future failures. Existing approaches for competence-aware planning are either model-based, requiring explicit enumeration of known
Multi-objective optimization models that encode ordered sequential constraints provide a solution to model various challenging problems including encoding preferences, modeling a curriculum, and enforcing measures of safety. A recently developed theory of topological Markov decision processes (TMDPs…
This paper presents a novel gradient ascent al-gorithm and nonlinear programming algorithm for finite state controller policies in constrained partially observable Markov decision processes (CPOMDPs). A key component of the gradient ascent algorithm is a constraint projection to ensure constraints a…
This paper presents a novel policy representation for partially observable Markov decision processes (POMDPs) called circulant controllers and a provably efficient gradient-based algorithm for them. A formal mathematical description is provided that leverages circulant matrices for the controller’s…
Due to the complexity of the real world, autonomous systems use decision-making models that rely on simplifying assumptions to make them computationally tractable and feasible to design. However, since these limited representations cannot fully capture the domain of operation, an autonomous system m…
We present a general policy formulation for partially observable Markov decision processes (POMDPs) called controller family policies that may be used as a framework to facilitate the design of new policy forms. We prove how modern approximate policy forms: point-based, finite state controller (FSC)…
We present the Goal Uncertain Stochastic Shortest Path (GUSSP) problem - a general framework to model path planning and decision making in stochastic environments with goal uncertainty. The framework extends the stochastic shortest path (SSP) model to dynamic environments in which it is impossible t…
We propose an algorithm called σ-approximation that compresses the non-zero values of beliefs for partially observable Markov decision processes (POMDPs) in order to improve performance and reduce memory usage. Specifically, we approximate individual belief vectors with a fixed bound on the number o…
We propose a log-space solution for robotic path planning with harmonic functions that solves the long-standing numerical precision problem. We prove that this algorithm: (1) performs the correct computations in log-space, (2) returns the true equivalent path using the log-space mapping, and (3) has…