Learning search polices from humans in a partially observable context
Graph Chatbot
Chat with Graph Search
Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.
DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.
The problem of control synthesis to maximize the probability of satisfying automata specifications for systems with uncertainty is addressed. Two types of uncertainty are considered; stochasticity in the dynamical system and in the sets defining the specif ...
From the moment we wake up in the morning to the day's ebb when we settle in to sleep, we are bound to the task of decision-making. Some of these decisions barely register in our consciousness, if at all, while others, less shy, take a more prominent place ...
Markov decision processes (MDPs) are powerful tools for decision making in uncertain dynamic environments. However, the solutions of MDPs are of limited practical use because of their sensitivity to distributional model parameters, which are typically unkn ...
One of the most fundamental problems in Markov decision processes is analysis and control synthesis for safety and reachability specifications. We consider the stochastic reach-avoid problem, in which the objective is to synthesize a control policy to max ...
Decision-making processes can be modulated by stress, and the time elapsed from stress induction seems to be a crucial factor in determining the direction of the effects. Although current approaches consider the first post-stress hour a uniform period, the ...
We sharpen an estimate of [4] for the topological degree of continuous maps from a sphere Sdinto itself in the case d >= 2. This provides the answer for d >= 2 to a question raised by Brezis. The problem is still open for d = 1. (C) 2017 Academie des scien ...
We consider a stylized core-periphery financial network in which links lead to the creation of projects in the outside economy but make banks prone to contagion risk. The controller seeks to maximize, under budget constraints, the value of the financial sy ...
Over the last few decades, rational health care management and, in particular, operating theater planning, has attracted increased attention from practitioners and from the scientific community. However, although the operating theater environment is clearl ...
We consider the problem of learning by demonstration from agents acting in unknown stochastic Markov environments or games. Our aim is to estimate agent preferences in order to construct improved policies for the same task that the agents are trying to sol ...
The spatial and temporal distribution of built space supply plays an important role in shaping urban form and thus the general travel pattern in an urban area. Within an integrated framework, we are interested in modeling the decisions of a builder in term ...