Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Quantum Decision Theory

Adam M. Brandenburger, Pierfrancesco La Mura

Published Jul 1, 2011• 2 citations
OpenAlex

Abstract

We argue that, contrary to conventional wisdom, decision theory is not invariant to the physical environment in which a decision is made. Specifically, we show that a decision maker (DM) with access to quantum information resources may be able to do strictly better than a DM with access only to classical information resources. In this respect, our findings are somewhat akin to those in computer science that have established the superiority of quantum over classical algorithms for certain problems. We treat three kinds of decision tree: (i) Kuhn trees ([24, 1950], [25, 1953]) in which the DM has perfect recall; (ii) Kuhn trees in which the DM has imperfect recall; and (iii) non-Kuhn trees.

Related papers

Incomplete information and quantum decision trees

Subhash C. Kak

This paper considers the problem of the absent-minded driver who must choose between alternatives with different payoff under the conditions of imperfect recall and varying degrees of knowledge of the system. We show that agents with access to quantum resources, or with a quantum mechanical basis, can obtain superior performance as compared to classical agents. The paper also considers the problem of random tree representations of quantum decision processes. It is shown that in the general case where each node can have any branching probability value, a random tree can accurately represent the probabilities associated with an arbitrary quantum state.

Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics•Oct 1, 2017•2 citations

Team decision problems with classical and quantum signals

Adam M. Brandenburger, Pierfrancesco La Mura

We study team decision problems where communication is not possible, but coordination among team members can be realized via signals in a shared environment. We consider a variety of decision problems that differ in what team members know about one another's actions and knowledge. For each type of decision problem, we investigate how different assumptions on the available signals affect team performance. Specifically, we consider the cases of perfectly correlated, i.i.d., and exchangeable classical signals, as well as the case of quantum signals. We find that, whereas in perfect-recall trees (Kuhn 1950 Proc. Natl Acad. Sci. USA 36, 570-576; Kuhn 1953 In Contributions to the theory of games, vol. II (eds H Kuhn, A Tucker), pp. 193-216) no type of signal improves performance, in imperfect-recall trees quantum signals may bring an improvement. Isbell (Isbell 1957 In Contributions to the theory of games, vol. III (eds M Drescher, A Tucker, P Wolfe), pp. 79-96) proved that, in non-Kuhn trees, classical i.i.d. signals may improve performance. We show that further improvement may be possible by use of classical exchangeable or quantum signals. We include an example of the effect of quantum signals in the context of high-frequency trading.

arXiv:1107.0237•Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences•Nov 30, 2015•19 citations

Quantum Decision Theory

Savo Glisic, Beatriz Lorenzo

One of the problems in quantum communications is the effective transmission of information over a noisy quantum channel, and there are several attempts in the literature to characterize the achievable rate of transmitting classical and quantum information over a noisy quantum channel. Classical game theory has been extensively used in modeling resource allocation in multi-operator wireless networks, especially the multi-operator strategies for acquisition of the spectrum. Quantum Game Theory models the behavior of strategic agents with access to quantum tools for controlling their strategies. Quantum Decision Theory (QDT) describes a decision maker's choice as a stochastic event occurring with a probability that is the sum of an objective utility factor and a subjective attraction factor. QDT offers a prediction for the average effect of subjectivity on decision makers, the quarter law. The chapter describes the general method for defining utility factors for a given set of lotteries containing both gains as well as losses.

Wiley eBooks•Feb 14, 2022•1 citation

Machine learning for decision-making under uncertainty

Lizhi Xin, Kevin Z. Xin, Houwen Xin

We live in a world brimming with uncertainty, where we constantly have to make a lot of decisions under incomplete information. We are firm believers that our subjective belief cannot be computed by rigorous mathematical formula; instead based on Darwin's natural selection (the evolution process is simulated by machine learning with genetic programming), a proposed computational model that incorporates insights from quantum theory to describe and explain decision-making under uncertainty. Unlike other decision-making theories that explain the decision-making process through probability theory, our proposed decision theory discovers "laws" of thought by learning observed historical data. There is no differential equation and no transition probability in our decision theory, our decision model has an emphasis on machine learning, where decision-makers build-up their experience by being rewarded or punished for each decision they make and prepare them for making better decisions in the future. We do not model with the usual utility function, but with quantum decision tree that simulates people's decision process. Each quantum decision tree includes a set of strategies; every time a decision is made, the decision-maker first chooses a strategy from the quantum decision tree's strategy pool, and then chooses an action based on the degree of belief which is obtained by genetic programming based on maximizing expected value.

arXiv:2212.04286•Dec 8, 2022•0 citations

Quantum computation and decision trees

Edward Farhi, Sam Gutmann

Many interesting computational problems can be reformulated in terms of decision trees. A natural classical algorithm is to then run a random walk on the tree, starting at the root, to see if the tree contains a node $n$ level from the root. We devise a quantum-mechanical algorithm that evolves a state, initially localized at the root, through the tree. We prove that if the classical strategy succeeds in reaching level $n$ in time polynomial in $n,$ then so does the quantum algorithm. Moreover, we find examples of trees for which the classical algorithm requires time exponential in $n,$ but for which the quantum algorithm succeeds in polynomial time. The examples we have so far, however, could also be solved in polynomial time by different classical algorithms.

arXiv:quant-ph/9706062•Physical Review A•Aug 1, 1998•1,232 citations

On Quantum Decision Trees

Subhash C. Kak

Quantum decision systems are being increasingly considered for use in artificial intelligence applications. Classical and quantum nodes can be distinguished based on certain correlations in their states. This paper investigates some properties of the states obtained in a decision tree structure. How these correlations may be mapped to the decision tree is considered. Classical tree representations and approximations to quantum states are provided.

arXiv:1703.03693•Mar 8, 2017•1 citation
We argue that, contrary to conventional wisdom, decision theory is not invariant to the physical environment in which a decision is made. Specifically, we show that a decision maker (DM) with access to quantum information resources may be able to do strictly better than a DM with access only to classical information resources. In this respect, our findings are somewhat akin to those in computer science that have established the superiority of quantum over classical algorithms for certain problems. We treat three kinds of decision tree: (i) Kuhn trees ([24, 1950], [25, 1953]) in which the DM has perfect recall; (ii) Kuhn trees in which the DM has imperfect recall; and (iii) non-Kuhn trees.
This paper considers the problem of the absent-minded driver who must choose between alternatives with different payoff under the conditions of imperfect recall and varying degrees of knowledge of the system. We show that agents with access to quantum resources, or with a quantum mechanical basis, can obtain superior performance as compared to classical agents. The paper also considers the problem of random tree representations of quantum decision processes. It is shown that in the general case where each node can have any branching probability value, a random tree can accurately represent the probabilities associated with an arbitrary quantum state.
We study team decision problems where communication is not possible, but coordination among team members can be realized via signals in a shared environment. We consider a variety of decision problems that differ in what team members know about one another's actions and knowledge. For each type of decision problem, we investigate how different assumptions on the available signals affect team performance. Specifically, we consider the cases of perfectly correlated, i.i.d., and exchangeable classical signals, as well as the case of quantum signals. We find that, whereas in perfect-recall trees (Kuhn 1950 Proc. Natl Acad. Sci. USA 36, 570-576; Kuhn 1953 In Contributions to the theory of games, vol. II (eds H Kuhn, A Tucker), pp. 193-216) no type of signal improves performance, in imperfect-recall trees quantum signals may bring an improvement. Isbell (Isbell 1957 In Contributions to the theory of games, vol. III (eds M Drescher, A Tucker, P Wolfe), pp. 79-96) proved that, in non-Kuhn trees, classical i.i.d. signals may improve performance. We show that further improvement may be possible by use of classical exchangeable or quantum signals. We include an example of the effect of quantum signals in the context of high-frequency trading.
One of the problems in quantum communications is the effective transmission of information over a noisy quantum channel, and there are several attempts in the literature to characterize the achievable rate of transmitting classical and quantum information over a noisy quantum channel. Classical game theory has been extensively used in modeling resource allocation in multi-operator wireless networks, especially the multi-operator strategies for acquisition of the spectrum. Quantum Game Theory models the behavior of strategic agents with access to quantum tools for controlling their strategies. Quantum Decision Theory (QDT) describes a decision maker's choice as a stochastic event occurring with a probability that is the sum of an objective utility factor and a subjective attraction factor. QDT offers a prediction for the average effect of subjectivity on decision makers, the quarter law. The chapter describes the general method for defining utility factors for a given set of lotteries containing both gains as well as losses.
We live in a world brimming with uncertainty, where we constantly have to make a lot of decisions under incomplete information. We are firm believers that our subjective belief cannot be computed by rigorous mathematical formula; instead based on Darwin's natural selection (the evolution process is simulated by machine learning with genetic programming), a proposed computational model that incorporates insights from quantum theory to describe and explain decision-making under uncertainty. Unlike other decision-making theories that explain the decision-making process through probability theory, our proposed decision theory discovers "laws" of thought by learning observed historical data. There is no differential equation and no transition probability in our decision theory, our decision model has an emphasis on machine learning, where decision-makers build-up their experience by being rewarded or punished for each decision they make and prepare them for making better decisions in the future. We do not model with the usual utility function, but with quantum decision tree that simulates people's decision process. Each quantum decision tree includes a set of strategies; every time a decision is made, the decision-maker first chooses a strategy from the quantum decision tree's strategy pool, and then chooses an action based on the degree of belief which is obtained by genetic programming based on maximizing expected value.
Many interesting computational problems can be reformulated in terms of decision trees. A natural classical algorithm is to then run a random walk on the tree, starting at the root, to see if the tree contains a node nnn level from the root. We devise a quantum-mechanical algorithm that evolves a state, initially localized at the root, through the tree. We prove that if the classical strategy succeeds in reaching level nnn in time polynomial in n,n,n, then so does the quantum algorithm. Moreover, we find examples of trees for which the classical algorithm requires time exponential in n,n,n, but for which the quantum algorithm succeeds in polynomial time. The examples we have so far, however, could also be solved in polynomial time by different classical algorithms.