An Architectural Framework for Integrated Multiagent Planning, Reacting, and Learning

Weiß, Gerhard

doi:10.1007/3-540-44631-1_22

Cited by 4 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These perspectives show some similarities to our work, but they don't incorporate a machine learning mechanism. (Weiβ, 2000) discusses the relationship between learning, planning and reacting, proposing an extension to a single-agent architectural framework to improve multi-agent coordination. The learning mechanism is used in order to determine the best way of alternating between reaction-based and plan-based coordination.…”

Section: Related Workmentioning

confidence: 99%

Using Cognition and Learning to Improve Agents’ Reactions

Graça

Gaspar

2003

Lecture Notes in Computer Science

View full text Add to dashboard Cite

This paper proposes an agent-architecture to deal with real-time problems where it is important both to react to constant changes in the state of the environment and to recognize the generic tendencies in the sequence of those changes. Reactivity must satisfy the need for immediate answers; cognition will enable the perception of medium and long time variations, allowing decisions that lead to an improved reactivity. Agents are able to evolve through an instance-based learning mechanism fed by the cognition process that allows them to improve their performance as they accumulate experience. Progressively, they learn to relate their ways of reacting (reaction strategies) with the general state of the environment. Using a simulation workbench that sets a distributed communication problem, different tests are made in an effort to evaluate: the utility of the multi-agent system architecture and the importance of the individual features of agents, the utility of using a set of different strategies, and the significance of the learning mechanism. The resulting conclusions point out the most significant aspects of the generic model adopted, helping to put it in perspective as a solution for other problems.

show abstract

Section: Related Workmentioning

confidence: 99%

Using Cognition and Learning to Improve Agents’ Reactions

Graça

Gaspar

2003

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…The results of these experiments show that M-Dyna-Q leads to a robust performance improvement over a variety of parameter settings. Some of the results are described in [4] (see http://wwwbrauer.in.tum.de/cgibin/make-fki-list.perl).…”

Section: Discussionmentioning

confidence: 99%

A multiagent variant of Dyna-Q

Weiss¹

Proceedings Fourth International Conference on MultiAgent Systems

View full text Add to dashboard Cite

This paper describes a multiagent variant of Dyna-Q called M-Dyna-Q. Dyna-Q is an integrated single-agent framework for planning, reacting, and learning. Like Dyna-Q, M-Dyna-Q employs two key ideas: learning results can serve as a valuable input for both planning and reacting, and results of planning and reacting can serve as a valuable input to learning. M-Dyna-Q extends Dyna-Q in that planning, reacting, and learning are jointly realized by multiple agents.

show abstract

Incremental Learning of Trust while Reacting and Planning

Froelich

Kisiel-Dorohinicki

Nawarecki

Advances and Innovations in Systems, Computing Sciences and Software Engineering

View full text Add to dashboard Cite

An Architectural Framework for Integrated Multiagent Planning, Reacting, and Learning

Cited by 4 publications

References 19 publications

Using Cognition and Learning to Improve Agents’ Reactions

Using Cognition and Learning to Improve Agents’ Reactions

A multiagent variant of Dyna-Q

Incremental Learning of Trust while Reacting and Planning

Contact Info

Product

Resources

About