Search
Now showing items 1-7 of 7
General self-motivation and strategy identification : Case studies based on Sokoban and Pac-Man
(2013-12-18)
In this paper, we use empowerment, a recently introduced biologically inspired measure, to allow an AI player to assign utility values to potential future states within a previously unencountered game without requiring ...
Perception-action loops of multiple agents : informational aspects and the impact of coordination
(2012)
Embodied agents can be conceived as entities perceiving and acting upon an external environment. Probabilistic models of this perception-action loop have paved the way to the investigation of information-theoretic aspects ...
Impoverished empowerment : `meaningful' action sequence generation through bandwidth limitation
(2011)
Empowerment is a promising concept to begin explaining how some biological organisms may assign apriori values expectations to states in taskless scenarios. Standard empowerment samples the full richness of an environment ...
Think globally, sense locally : From local information to global features
(Institute of Electrical and Electronics Engineers (IEEE), 2011)
Shannon's information theory can be used to quantify morphological and topological features of a collective of agents in an arbitrary environment. In particular the ability of individual agents to extract information locally ...
Hierarchical behaviours : getting the most bang for your bit
(2011)
Hierarchical structuring of behaviour is prevalent in natural and artificial agents and can be shown to be useful for learning and performing tasks. To progress systematic understanding of these benefits we study the effect ...
What do You Want to do Today? : Relevant-Information Bookkeeping in Goal-Oriented Behaviour
(MIT Press, 2010)
We extend existing models and methods for the informational treatment of the perception-action loop to the case of goaloriented behaviour and introduce the notion of relevant goal information as the amount of information ...
Two Agents Acting as One
(MIT Press, 2010)
We consider two agents, each equipped with a controller. When they achieve a joint goal configuration, their coordination can be measured informationally. We show that the amount of coordination that two agents need to ...