Results 1 - 10 of 4,091

Transfer of Learning by Composing Solutions of Elemental Sequential Tasks

by Satinder Pal Singh - Machine Learning , 1992
"... Although building sophisticated learning agents that operate in complex environments will require learning to perform multiple tasks, most applications of reinforcement learning have focussed on single tasks. In this paper I consider a class of sequential decision tasks (SDTs), called composite sequ ..."
Abstract - Cited by 180 (8 self) - Add to MetaCart
Although building sophisticated learning agents that operate in complex environments will require learning to perform multiple tasks, most applications of reinforcement learning have focussed on single tasks. In this paper I consider a class of sequential decision tasks (SDTs), called composite

Information reduction in the analysis of sequential tasks

by Michael I. Posner - Psychological Review , 1964
"... This paper proposes a taxonomy of information-processing tasks. Information conserving, reducing, and creating operations are viewed as different methods of processing. The main concern of this paper is information reduction which, it is suggested, represents a kind of thinking in which the solution ..."
Abstract - Cited by 23 (0 self) - Add to MetaCart
This paper proposes a taxonomy of information-processing tasks. Information conserving, reducing, and creating operations are viewed as different methods of processing. The main concern of this paper is information reduction which, it is suggested, represents a kind of thinking in which

A Sequential Algorithm for Training Text Classifiers

by David D. Lewis, William A. Gale , 1994
"... The ability to cheaply train text classifiers is critical to their use in information retrieval, content analysis, natural language processing, and other tasks involving data which is partly or fully textual. An algorithm for sequential sampling during machine learning of statistical classifiers was ..."
Abstract - Cited by 631 (10 self) - Add to MetaCart
The ability to cheaply train text classifiers is critical to their use in information retrieval, content analysis, natural language processing, and other tasks involving data which is partly or fully textual. An algorithm for sequential sampling during machine learning of statistical classifiers

Sequential Task Execution in a Minimalist Distributed

by Robotic System Chris , 2002
"... The collective execution of a single task, such as foraging or clustering, has received considerable research attention in the minimalist distributed robotic systems (MDRS) community. In contrast, achievement of sequential tasks by MDRS has so far been considered in only a handful of studies. ..."
Abstract - Add to MetaCart
The collective execution of a single task, such as foraging or clustering, has received considerable research attention in the minimalist distributed robotic systems (MDRS) community. In contrast, achievement of sequential tasks by MDRS has so far been considered in only a handful of studies.

Learning Sequential Tasks by Incrementally Adding Higher Orders

by Mark Ring - Advances in Neural Information Processing Systems 5 , 1993
"... An incremental, higher-order, non-recurrent network combines two properties found to be useful for learning sequential tasks: higherorder connections and incremental introduction of new units. The network adds higher orders when needed by adding new units that dynamically modify connection weights. ..."
Abstract - Cited by 33 (6 self) - Add to MetaCart
An incremental, higher-order, non-recurrent network combines two properties found to be useful for learning sequential tasks: higherorder connections and incremental introduction of new units. The network adds higher orders when needed by adding new units that dynamically modify connection weights

Bundling decisions in procurement auction with sequential tasks

by Sanxi Li , Jun Yu
"... Abstract This paper investigates the principal's bundling decision in procurement auction in the context of a project consisting of two sequential tasks, where task externality exists and information arrives sequentially. We show that although increasing in the number of bidders in the market ..."
Abstract - Add to MetaCart
Abstract This paper investigates the principal's bundling decision in procurement auction in the context of a project consisting of two sequential tasks, where task externality exists and information arrives sequentially. We show that although increasing in the number of bidders in the market

Autonomous Learning of Sequential Tasks: Experiments and Analyses

by Ron Sun, Todd Peterson - IEEE Transactions on Neural Networks , 1998
"... : This paper presents a novel learning model Clarion, which is a hybrid model based on the twolevel approach proposed in Sun (1995). The model integrates neural, reinforcement, and symbolic learning methods to perform on-line, bottom-up learning (i.e., learning that goes from neural to symbolic repr ..."
Abstract - Cited by 52 (30 self) - Add to MetaCart
representations). The model utilizes both procedural and declarative knowledge (in neural and symbolic representations respectively), tapping into the synergy of the two types of processes. It was applied to deal with sequential decision tasks. Experiments and analyses in various ways are reported that shed light

Transfer of Learning Across Compositions of Sequential Tasks

by Satinder Singh - Machine Learning: Proceedings of the Eighth International Workshop , 1991
"... Most "weak" learning algorithms, including reinforcement learning methods, have been applied on tasks with single goals. The effort to build more sophisticated learning systems that operate in complex environments will require the ability to handle multiple goals. Methods that allow transf ..."
Abstract - Cited by 15 (1 self) - Add to MetaCart
Most "weak" learning algorithms, including reinforcement learning methods, have been applied on tasks with single goals. The effort to build more sophisticated learning systems that operate in complex environments will require the ability to handle multiple goals. Methods that allow

Sequential Task Execution in a Minimalist Distributed Robotic System

by Chris Jones, Maja J. Matarić - Proceedings of the Simulation of Adaptive Behavior
"... The collective execution of a single task, such as foraging or clustering, has received considerable research attention in the minimalist distributed robotic systems (MDRS) community. In contrast, achievement of sequential tasks by MDRS has so far been considered in only a handful of studies. Sequen ..."
Abstract - Cited by 4 (0 self) - Add to MetaCart
The collective execution of a single task, such as foraging or clustering, has received considerable research attention in the minimalist distributed robotic systems (MDRS) community. In contrast, achievement of sequential tasks by MDRS has so far been considered in only a handful of studies

Transfer of Learning by Composing Solutions of Elemental Sequential Tasks

by Satinder Pal - Machine Learning , 1992
"... Although building sophisticated learning agents that operate in complex environments will require learning to perform multiple tasks, most applications of reinforcement learning have focussed on single tasks. In this paper I consider a class of sequential decision tasks (SDTs), called composite sequ ..."
Abstract - Add to MetaCart
Although building sophisticated learning agents that operate in complex environments will require learning to perform multiple tasks, most applications of reinforcement learning have focussed on single tasks. In this paper I consider a class of sequential decision tasks (SDTs), called composite
Results 1 - 10 of 4,091