Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data. A simulation from public publication records: the people listed were not invited and did not agree to review.
? Tutorial for this page
Demo Data from VLDB 2026 / reviewers in the wild / expert

Brian Sallans

dblp:75/1641 · DBLP profile ↗
← Back
3ranked-venue papers
3as first author
0since 2021 · last 2004
—ORCID · none

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 3 · 3 first-author

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Artificial intelligence
3 papers
Reinforcement learning · 75% Representation and self-supervised learning · 12% Planning, search and constraint satisfaction · 10%

Topics — the 10 heaviest of 10, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Machine learning › Reinforcement learning
factored reinforcement learning		 0.012004
Reinforcement Learning with Factored States and Actions · J. Mach. Learn. Res. 2004
Machine learning › Reinforcement learning › markov decision process
factored markov decision process		 0.022004
Using Free Energies to Represent Q-values in a Multiagent Reinforcement Learning Task · NIPS 2000
Reinforcement Learning with Factored States and Actions · J. Mach. Learn. Res. 2004
Machine learning › Reinforcement learning
multi-agent reinforcement learning		 0.012000
Using Free Energies to Represent Q-values in a Multiagent Reinforcement Learning Task · NIPS 2000
Machine learning › Reinforcement learning › value-based reinforcement learning
q-learning		 0.012000
Using Free Energies to Represent Q-values in a Multiagent Reinforcement Learning Task · NIPS 2000
Machine learning › Reinforcement learning
value function approximation		 0.012000
Using Free Energies to Represent Q-values in a Multiagent Reinforcement Learning Task · NIPS 2000
Machine learning › Representation and self-supervised learning
factored representation		 0.011999
Learning Factored Representations for Partially Observable Markov Decision Processes · NIPS 1999
Knowledge, reasoning and agents › Planning, search and constraint satisfaction › planning under uncertainty
partially observable markov decision process		 0.011999
Learning Factored Representations for Partially Observable Markov Decision Processes · NIPS 1999
Machine learning › Reinforcement learning
markov decision process		 0.012004
Reinforcement Learning with Factored States and Actions · J. Mach. Learn. Res. 2004
Machine learning › Generative modeling › generative model › probabilistic generative model
product of experts		 0.012000
Using Free Energies to Represent Q-values in a Multiagent Reinforcement Learning Task · NIPS 2000
Machine learning › Representation and self-supervised learning
factorized representation learning		 0.011999
Learning Factored Representations for Partially Observable Markov Decision Processes · NIPS 1999

Methods — techniques the papers use, named apart from their topics

gibbs sampling · 0.0free energy · 0.0SARSA · 0.0
YearPublicationVenuePosition
2004 Reinforcement Learning with Factored States and Actions
Brian Sallans, Geoffrey E. Hinton
 J. Mach. Learn. Res.1
2000 Using Free Energies to Represent Q-values in a Multiagent Reinforcement Learning Task
abstract
The problem of reinforcement learning in large factored Markov decision processes is explored. The Q-value of a state-action pair is approximated by the free energy of a product of experts network. Network parameters are learned on-line using a modified SARSA algorithm which minimizes the inconsistency of the Q-values of consecutive state-action pairs. Ac(cid:173) tions are chosen based on the current value estimates by fixing the current state and sampling actions from the network using Gibbs sampling. The algorithm is tested on a co-operative multi-agent task. The product of experts model is found to perform comparably to table-based Q-Iearning for small instances of the task, and continues to perform well when the problem becomes too large for a table-based representation.
Brian Sallans, Geoffrey E. Hinton
 NIPS1
1999 Learning Factored Representations for Partially Observable Markov Decision Processes
Brian Sallans
 NIPS1