Mark B. Ring

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.

VLDB 2026 Research / reviewers in the wild / expert

dblp:75/6510 · DBLP profile ↗

← Back

8ranked-venue papers

5as first author

0since 2021 · last 2013

—ORCID · none

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

Artificial intelligence and machine learning · 8 · 5 first-authorGraphics, computer vision, multimedia, augmented reality and games · 3 · 1 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 5 papers		Reinforcement learning · 75% Representation and self-supervised learning · 19% Learning theory · 6%
Theoretical computer science 1 paper		Automata and formal languages · 100%

Topics — the 11 heaviest of 13, each with the papers that count most for it

Topic	Weight	Papers	Last	Evidence papers
Machine learning › Representation and self-supervised learning › feature transformation feature construction	0.1	1	2011	Incremental Basis Construction from Temporal Difference Error · ICML 2011
Machine learning › Reinforcement learning temporal difference learning	0.1	1	2011	Incremental Basis Construction from Temporal Difference Error · ICML 2011
Machine learning › Reinforcement learning value function approximation	0.1	1	2011	Incremental Basis Construction from Temporal Difference Error · ICML 2011
Machine learning › Reinforcement learning › function approximation › representation learning for reinforcement learning predictive representations	0.1	1	2005	Using Predictive Representations to Improve Generalization in Reinforcement Learning · IJCAI 2005
Machine learning › Learning theory › statistical estimation error estimation	0.0	1	2011	Q-Error as a Selection Mechanism in Modular Reinforcement-Learning Systems · IJCAI 2011
Machine learning › Reinforcement learning value-based reinforcement learning	0.0	1	2011	Q-Error as a Selection Mechanism in Modular Reinforcement-Learning Systems · IJCAI 2011
Automata and formal languages cellular automata	0.0	1	1997	RCC Cannot Compute Certain FSA, Even with Arbitrary Transfer Functions · NIPS 1997
Machine learning › Reinforcement learning generalization in reinforcement learning	0.0	1	2005	Using Predictive Representations to Improve Generalization in Reinforcement Learning · IJCAI 2005
Machine learning › Reinforcement learning sequential task learning	0.0	1	1992	Learning Sequential Tasks by Incrementally Adding Higher Orders · NIPS 1992
Automata and formal languages finite automata	0.0	1	1997	RCC Cannot Compute Certain FSA, Even with Arbitrary Transfer Functions · NIPS 1997
Machine learning › Representation and self-supervised learning › representation learning hierarchical learning	0.0	1	1992	Learning Sequential Tasks by Incrementally Adding Higher Orders · NIPS 1992

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

linear function approximation · 0.1incremental basis construction · 0.1predictive state representation · 0.1transfer function · 0.0incremental learning · 0.0incremental development · 0.0

Year	Publication	Venue	Position
2013	Better Generalization with Forecasts Tom Schaul, Mark B. Ring	IJCAI	2
2011	Incremental Basis Construction from Temporal Difference Error Yi Sun 0003, Faustino J. Gomez, Mark B. Ring, Jürgen Schmidhuber	ICML	3
2011	Q-Error as a Selection Mechanism in Modular Reinforcement-Learning Systems abstract This paper introduces a novel multi-modular method for reinforcement learning. A multimodular system is one that partitions the learning task among a set of experts (modules), where each expert is incapable of solving the entire task by itself. There are many advantages to splitting up large tasks in this way, but existing methods face difficulties when choosing which module(s) should contribute to the agent’s actions at any particular moment. We introduce a novel selection mechanism where every module, besides calculating a set of action values, also estimates its own error for the current input. The selection mechanism combines each module’s estimate of long-term reward and self-error to produce a score by which the next module is chosen. As a result, the modules can use their resources effectively and efficiently divide up the task. The system is shown to learn complex tasks even when the individual modules use only linear function approximators. 1 Mark B. Ring, Tom Schaul	IJCAI	1
2005	Using Predictive Representations to Improve Generalization in Reinforcement Learning Eddie J. Rafols, Mark B. Ring, Richard S. Sutton, Brian Tanner	IJCAI	2
1997	RCC Cannot Compute Certain FSA, Even with Arbitrary Transfer Functions Mark B. Ring	NIPS	1
1997	CHILD: A First Step Towards Continual Learning Mark B. Ring	Mach. Learn.	1
1992	Learning Sequential Tasks by Incrementally Adding Higher Orders Mark B. Ring	NIPS	1
1991	Incremental Development of Complex Behaviors Mark B. Ring	ML	1