Learning to sense selectively in physical domains

@inproceedings{Langley1997LearningTS,
  title={Learning to sense selectively in physical domains},
  author={Pat Langley},
  booktitle={International Conference on Autonomous Agents},
  year={1997},
  url={https://api.semanticscholar.org/CorpusID:3511022}
}
Icarus is presented, an architecture that represents control knowledge in terms of durative states and sequences of such states that operates in cycles, activating a state that matches the environmental situation and letting that state control behavior until its conditions fail or until nding another matching state with higher priority.
View on ACM
doi.org
7 Citations
Highly Influential Citations
1
Background Citations
5
Methods Citations
2

7 Citations

Symbolic performance and learning in continuous-valued environments

Real-world and simulated real-world domains, such as flying and driving, commonly have the characteristics of continuous-valued (CV) environments. These environments are frequently complex and…

Influencing robot learning through design and social interactions : a framework for balancing designer effort with active and explicit interactions

It is argued that characterising the balance between designer effort and social interactions and how learning performance is affected is crucial for addressing a difficult trade-off: increasing designer effort for biasing the learning of a particular task in a particular environment and thus providing more reliability, versus increasing the influence from the social interactions Thus providing more generality.

Behavior and path planning for the coalition of cognitive robots in smart relocation tasks

Cognitive approach is used and semiotic knowledge representation—sign world model is introduced which underlines behavioral planning methodology and planning is viewed as a recursive search process in the hierarchical state-space induced by sings with path planning signs residing on the lowest level.

Controlling physical agents through reactive logic programming

This paper describes Icarus, a language for specifying the behavior of agents that operate in physical domains. This language provides a novel metaphor of “reactive logic programming”, which makes it…

Adaptive Conversational Agents for Task-Oriented Dialogues

This paper describes ongoing research on an adaptive conversational agent supporting task-oriented dialogues that integrates natural language understanding technology with an adaptive ability to reason about and carry out dialogues.

Evolution of the Icarus Cognitive Architecture

Scientific process.

24 References

Learning to Plan in Continuous Domains

A general theory of discrimination learning

It is shown how the theory of discrimination learning can be applied to the domains of concept attainment, strategy learning, first language acquisition, and cognitive development and is evaluated along the dimensions of simplicity, generality, and fertility.

Inductive Learning of Reactive Action Models

Hierarchical Learning in Stochastic Domains: Preliminary Results

Learning Monitoring Strategies to Compensate for Model Uncertainty

This paper addresses the need for monitoring the environment given an action model that is uncertain or stochastic. Its contribution is to describe how monitoring costs can be included in the…

Sensible Planning: Focusing Perceptual Attention

This paper outlines an approach to the efficient construction of plans containing explicit sensing operations with the objective of finding nearly optimal cost effective plans with respect to both action and sensing.

Experiments in Optimal Sensing for Situated Agents

The results indicate that static sensing policies can be successful, provided that the rate of change in the environment and the cost of sensor processing do not vary too greatly.

An Analysis of Error Recovery and Sensory Integration for Dynamic Planners

Close-form formulas for the appropriate frequency of sensor integration as a function of parameters of the equipment, the domain, and the types of errors from which the system wishes to recover are derived.

Commonsense Reasoning about Causality: Deriving Behavior from Structure

Quantitative Results Concerning the Utility of Explanation-based Learning