Results 261 to 270 of about 154,271 (296)
Some of the next articles are maybe not open access.
On Adaptivity and Safety in Sequential Decision Making
Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, 2023Sequential decision making is an important field in machine learning, encompassing techniques such as online optimization, structured bandits, and reinforcement learning, which have numerous applications such as recommendation systems, online advertising, conversational agents, and robot learning.
openaire +1 more source
A Semantic Framework for Sequential Decision Making [PDF]
, 2015 Current developments in the medical domain, not unlike many other sectors, are marked by the growing digitalisation of data, including patient records, study results, clinical guidelines or imagery. This trend creates the opportunity for the development of innovative decision support systems to assist physicians in making a diagnosis or preparing a ...
Patrick Philipp 0002 +3 more
openaire +2 more sources
Sequential Decision Making With Coherent Risk
IEEE Transactions on Automatic Control, 2017We provide sampling-based algorithms for optimization under a coherent-risk objective. The class of coherent-risk measures is widely accepted in finance and operations research, among other fields, and encompasses popular risk-measures such as conditional value at risk and mean-semi-deviation.
Aviv Tamar +3 more
openaire +1 more source
Representation Discovery in Sequential Decision Making
Proceedings of the AAAI Conference on Artificial Intelligence, 2010Automatically constructing novel representations of tasks from analysis of state spaces is a longstanding fundamental challenge in AI. I review recent progress on this problem for sequential decision making tasks modeled as Markov decision processes.
openaire +1 more source
Multiattribute Decision Making by Sequential Resource Allocation
Operations Research, 1980A new approach is proposed for addressing decision problems in which the outcomes are multidimensional and possibly interdependent. The method is based on decomposing the problem into a sequence of simpler decision problems. The solution to each subproblem is elicited from the decision-maker by converting it to a simple resource allocation task that ...
Peter A. Morris, Shmuel S. Oren
openaire +2 more sources
1999
In this chapter we will focus on sequential decision problems that must be made in the presence of informed uncertainty; that is, uncertainty that can be quantified with probability distributions (also called decision making under risk). These sequential decisions will result in a sequence of actions, also referred to as policies.
openaire +1 more source
In this chapter we will focus on sequential decision problems that must be made in the presence of informed uncertainty; that is, uncertainty that can be quantified with probability distributions (also called decision making under risk). These sequential decisions will result in a sequence of actions, also referred to as policies.
openaire +1 more source
Decision Making in a Sequential Game
Journal of Sports Economics, 2012This article uses data from NASCAR to examine strategic decision making with professional players and high stakes. The authors look at driver decisions to pit, enabling car performance to be improved at the cost of track position. Unlike other sports choices that have been used to test game-theoretic play, pitting decisions occur sequentially ...
Deck, Alan, Deck, Cary, Zhu, Zhen
openaire +2 more sources
GSMDPs for Multi-Robot Sequential Decision-Making
Proceedings of the AAAI Conference on Artificial Intelligence, 2013Markov Decision Processes (MDPs) provide an extensive theoretical background for problems of decision-making under uncertainty. In order to maintain computational tractability, however, real-world problems are typically discretized in states and actions as well as in time.
João Vicente Messias +2 more
openaire +1 more source
Sequential Decision Making in Artificial Musical Intelligence
Proceedings of the AAAI Conference on Artificial Intelligence, 2018My main research motivation is to develop complete autonomous agents that interact with people socially. For an agent to be social with respect to humans, it needs to be able to parse and process the multitude of aspects that comprise the human cultural experience. That in itself gives rise to many fascinating learning problems.
openaire +2 more sources