Related papers: Explanation through Reward Model Reconciliation us…
Partially observable Markov decision processes (POMDP) are a useful model for decision-making under partial observability and stochastic actions. Partially Observable Monte-Carlo Planning is an online algorithm for deciding on the next…
Autonomous vehicles (AVs) need to interact with other traffic participants who can be either cooperative or aggressive, attentive or inattentive. Such different characteristics can lead to quite different interactive behaviors. Hence, to…
Autonomous agents that operate in the real world must often deal with partial observability, which is commonly modeled as partially observable Markov decision processes (POMDPs). However, traditional POMDP models rely on the assumption of…
In human-robot collaboration, the objectives of the human are often unknown to the robot. Moreover, even assuming a known objective, the human behavior is also uncertain. In order to plan a robust robot behavior, a key preliminary question…
Partially observable Markov decision processes (POMDPs) offer a principled formalism for planning under state and transition uncertainty. Despite advances made towards solving large POMDPs, obtaining performant policies under limited…
Intention recognition, or the ability to anticipate the actions of another agent, plays a vital role in the design and development of automated assistants that can support humans in their daily tasks. In particular, industrial settings pose…
In this paper, we present algorithms that perform gradient ascent of the average reward in a partially observable Markov decision process (POMDP). These algorithms are based on GPOMDP, an algorithm introduced in a companion paper (Baxter…
Active classification, i.e., the sequential decision-making process aimed at data acquisition for classification purposes, arises naturally in many applications, including medical diagnosis, intrusion detection, and object tracking. In this…
This paper presents a philosophical and experimental study of fairness interventions in AI classification, centered on the explainability of corrective methods. We argue that ensuring fairness requires not only satisfying a target…
Inferring reward functions from human behavior is at the center of value alignment - aligning AI objectives with what we, humans, actually want. But doing so relies on models of how humans behave given their objectives. After decades of…
We study planning problems where autonomous agents operate inside environments that are subject to uncertainties and not fully observable. Partially observable Markov decision processes (POMDPs) are a natural formal model to capture such…
We study observation-based strategies for partially-observable Markov decision processes (POMDPs) with omega-regular objectives. An observation-based strategy relies on partial information about the history of a play, namely, on the past…
There is a growing interest in designing autonomous agents that can work alongside humans. Such agents will undoubtedly be expected to explain their behavior and decisions. While generating explanations is an actively researched topic, most…
We present a technique for speeding up the convergence of value iteration for partially observable Markov decisions processes (POMDPs). The underlying idea is similar to that behind modified policy iteration for fully observable Markov…
Explainable Artificial Intelligence (XAI) has become critical in enhancing the transparency and trustworthiness of AI systems, especially as these systems are increasingly deployed in high-stakes domains such as healthcare and finance.…
Machine learning models are increasingly integrated into societally critical applications such as recidivism prediction and medical diagnosis, thanks to their superior predictive power. In these applications, however, full automation is…
Partially observable Markov decision processes (POMDPs) are a general mathematical model for sequential decision-making in stochastic environments under state uncertainty. POMDPs are often solved \textit{online}, which enables the algorithm…
We consider a planning problem where the dynamics and rewards of the environment depend on a hidden static parameter referred to as the context. The objective is to learn a strategy that maximizes the accumulated reward across all contexts.…
Robots need models of human behavior for both inferring human goals and preferences, and predicting what people will do. A common model is the Boltzmann noisily-rational decision model, which assumes people approximately optimize a reward…
Partially Observable Markov Decision Process (POMDP) is widely used to model probabilistic behavior for complex systems. Compared with MDPs, POMDP models a system more accurate but solving a POMDP generally takes exponential time in the…