Spier, E (1997) From Reactive Behaviour to Adaptive Behaviour. PhD Thesis, Balliol College, Oxford. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Pigs and People - Pauls (2001) (2 citations) (Correct)
....using reinforcement learning. In Sutton s mechanism, a single process executes alternately on a model of the world, and the real world. He introduces Dyna architectures which combine learning and planning into a single process, and tests his mechanism in a simple environment. Additionally, Spier, 97] and [Spier and McFarland, 97] use drk, a reactive motivational model as an action selection mechanism, and extend it with reinforcement learning. This work is especially interesting from a biological point of view, as it focuses on reproducing behaviours observable in real animals. We can ....
Spier, E. 1997. From Reactive Behaviour to Adaptive Behaviour. University of Oxford, PhD thesis.
Learning To Do Without Cognition - Spier, McFarland (3 citations) Self-citation (Spier) (Correct)
....model called the drk model (Spier and McFarland, 1996) with some simple reinforcement learning rules and uses an instantation of this model as the control system of an animat in a computer simulation of a Skinner box. Such a model is amenable to implementation on real robots (McFarland and Spier, 1997). In section 2 there is an overview of the outcome devaluation effect, the phenomenon in question, and a discussion of previously offered explanations and their implications. Subsequently, section 3 provides a brief overview of the drk model, section 4 offers a theoretical account of how the drk ....
.... internal state variables 2 , say h for hunger and t for thirst; this is expressed by the deficit vector d = d h ; d t ) In the case of an animat the physiological state space would be those factors that the agent could measure that were correlated with its fundamental tasks, McFarland and Spier (1997) discuss a robot with a state space consisting of energy and work performed. From previous experience the agent has built a table r of associations that link externally sensed resources to changes in its internal state (their availabilities) e.g. r = r Ph r Sh r P t r St where the columns ....
[Article contains additional citation context not shown here]
Spier, E. (1997). From reactive behaviour to adaptive behaviour: Motivational models for behaviour in animals and robots. D.Phil. thesis, Department of Zoology, Oxford University. Also available at http://www.cogs.sussex.ac.uk/users/emmet .
Motivated Reinforcement Learning - Dayan (2001) (2 citations) (Correct)
No context found.
Spier, E (1997) From Reactive Behaviour to Adaptive Behaviour. PhD Thesis, Balliol College, Oxford.
Motivation Driven Learning for Interactive Synthetic.. - Yoon, Blumberg, Schneider (2000) (5 citations) (Correct)
No context found.
Spier, E. H. From Reactive Behaviour to Adaptive Behaviour: Motivational models for behaviour in animals and robots. Ph. D. Thesis. Balliol College, University of Oxford, 1997.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC