Multi-shot pedestrian re-identification problem is at the core of surveillance video analysis. It matches two tracks of pedestrians from different cameras. In contrary to existing works that aggregate single frames features by time series model such as recurrent neural network, in this paper, we propose an interpretable reinforcement learning based approach to this problem. Particularly, we tra...

Decision making can be a complex task involving a sequence of subdecisions. For example, we decide to pursue a goal (e.g., get something to eat), then decide how to accomplish that goal (e.g., go to a restaurant), and then make a sequence of more specific plans (e.g., which restaurant to go to, how to get there, what to order, etc.). In characterizing the effects of stimulating individual brain...

Learning probability distributions on the weights of neural networks (NNs) has recently proven beneficial in many applications. Bayesian methods, such as Stein variational gradient descent (SVGD), offer an elegant framework to reason about NN model uncertainty. However, by assuming independent Gaussian priors for the individual NN weights (as often applied), SVGD does not impose prior knowledge...

POMDPs.jl is an open-source framework for solving Markov decision processes (MDPs) and partially observable MDPs (POMDPs). POMDPs.jl allows users to specify sequential decision making problems with minimal effort without sacrificing the expressive nature of POMDPs, making this framework viable for both educational and research purposes. It is written in the Julia language to allow flexible prot...

We axiomatically characterise a class of algorithms for making sequential decisions in situations of complete ignorance. These algorithms assume that a decision maker (DM) (human or or a software agent) has exogenously defined utilities for prizes and she uses the empirical distribution of prizes to calculate the “expected utility” of each action maximising this expected utility at each stage o...

*Correspondence: [email protected]; [email protected] 1GRASP Laboratory, Electrical and Systems Engineering Department, University of Pennsylvania, Philadelphia, PA 19104, USA 2Max Planck Institute for Biological Cybernetics and Max Planck Institute for Intelligent Systems, Speemanstrasse 38, Tübingen 72076, Germany Abstract Purpose: Sampling an action according to the probability ...

The problem of making decisions is ubiquitous in life. This problem becomes even more complex when the decisions should be made sequentially. In fact, the execution of an action at a given time leads to a change in the environment of the problem, and this change cannot be predicted with certainty. The aim of a decision-making process is to optimally select actions in an uncertain environment. T...

Most real-life decisions are made with less than perfect information and there is often some opportunity to acquire additional information to increase the quality of the decision. In this article, we define and study the sequential information acquisition process of a rational decision maker (DM) when allowed to acquire any finite amount of information from a set of products defined by vectors ...

BACKGROUND In a recent controversial essay, published by JPA Ioannidis in PLoS Medicine, it has been argued that in some research fields, most of the published findings are false. Based on theoretical reasoning it can be shown that small effect sizes, error-prone tests, low priors of the tested hypotheses and biases in the evaluation and publication of research findings increase the fraction of...

In cooperative multiagent planning, it can often be beneficial for an agent to make commitments about aspects of its behavior to others, allowing them in turn to plan their own behaviors without taking the agent’s detailed behavior into account. Extending previous work in the Bayesian setting, we consider instead a worst-case setting in which the agent has a set of possible environments (MDPs) ...