@inproceedings{dijk_informational_2012,
  author = {van Dijk, Sander G. and Polani, D},
  title = {Informational Drives for Sensor Evolution},
  booktitle = {Artificial Life XIII: The 13th International Conference on
		  the Synthesis and Simulation of Living Systems},
  year = {2012},
  note = {Accepted},
  abstract = { It has been hypothesized that the evolution of sensors is
		  a pivotal driver for the evolution of organisms, and
		  especially, as a crucial part of the perception-action
		  loop, a driver for cognitive development. The questions of
		  why and how this is the case are important: what are the
		  principles that push the evolution of sensorimotor systems?
		  An interesting aspect of this problem is the cooption of
		  sensors for functions other than those originally driving
		  their development (e.g. the auditive sense of bats being
		  employed as a `visual' modality). Even more striking is the
		  phenomenon found in nature of sensors being driven to the
		  limits of precision, while starting from much simpler
		  beginnings. While a large potential for diversification and
		  exaptation is visible in the observed phenotypes, gaining a
		  deeper understanding of why and how this can be achieved is
		  a significant problem. In this present paper, we will
		  introduce an abstract and generic information-theoretic
		  model for understanding potential drives of sensor
		  evolution, both in terms of improving sensoric ability and
		  in terms of extending and/or shifting sensoric function.},
  owner = {sander},
  timestamp = {2012.05.02}
}

@inproceedings{dijk_grounding_2011,
  author = {van Dijk, Sander G. and Polani, Daniel},
  title = {{Grounding Subgoals in Information Transitions}},
  booktitle = {IEEE Symposium on Adaptive Dynamic Programming and
		  Reinforcement Learning},
  year = {2011},
  pages = {105--111},
  address = {Paris, France},
  abstract = {In reinforcement learning problems, the construction of
		  subgoals has been identified as an important step to speed
		  up learning and to enable skill transfer. For this purpose,
		  one typically extracts states from various saliency
		  properties of an MDP transition graph, most notably
		  bottleneck states. Here we introduce an alternative
		  approach to this problem: assuming a family of MDPs with
		  multiple goals but with a fixed transition graph, we
		  introduce the relevant goal information as the amount of
		  Shannon information that the agent needs to maintain about
		  the current goal at a given state to select the appropriate
		  action. We show that there are distinct transition states
		  in the MDP at which new relevant goal information has to be
		  considered for selecting the next action. We argue that
		  these transition states can be interpreted as subgoals for
		  the current task class, and we use these states to
		  automatically create a hierarchical policy, according to
		  the well-established Options model for hierarchical
		  reinforcement learning.},
  url = {http://homepages.stca.herts.ac.uk/~sv08aav/pub/vandijk.ieeeadprl11.subgoals.pdf}
}

@inproceedings{dijk_look_2011,
  author = {van Dijk, Sander G. and Polani, Daniel},
  title = {{Look-Ahead Relevant Information: Reducing Cognitive
		  Burden over Prolonged Tasks}},
  booktitle = {IEEE Symposium on Artificial Life},
  year = {2011},
  pages = {46--53},
  address = {Paris, France},
  abstract = {Based on the fact that information processing is costly,
		  we study in this paper the trade-off between performance
		  and informational requirements. Most importantly, we are
		  interested in how local decisions can alleviate future
		  cognitive burden, measured by the amount of sensory
		  information an agent processes, without conceding
		  performance. We introduce \emph{look-ahead information} as
		  a novel concept to capture the long-term informational
		  requirements and present an iterative method to determine
		  the value of this quantity. Using an example problem, we
		  show how these long-term considerations enable an agent to
		  predict future effects of its actions on its informational
		  burden, and to shape the course of the world to achieve
		  more informationally parsimonious behaviour.},
  url = {http://homepages.stca.herts.ac.uk/~sv08aav/pub/vandijk.ieeealife11.lookahead.pdf}
}

@inproceedings{lattarulo_application_2011,
  author = {Lattarulo, Valerio and van Dijk, Sander G.},
  title = {{Application of the ``Alliance Algorithm'' to Energy
		  Constrained Gait Optimization}},
  booktitle = {The 15th Annual RoboCup International Symposium},
  year = {2011},
  pages = {393--404},
  address = {Istanbul, Turkey},
  abstract = {This paper deals with the problem of energy constrained
		  gait optimization for bipedal walking. We present a
		  solution to this problem obtained by applying a recently
		  introduced heuristic method, the Al- liance Algorithm (AA),
		  and compare its performance against a Genetic Algorithm
		  (GA). We show experimentally that the intrinsic ability of
		  the AA to handle hard constraints enables it to find
		  solutions signifi- cantly better than the GA. Also with the
		  constraint removed the AA show more reliable optimization
		  results. Finally, we show that the final gait obtained
		  through this method outperforms most solutions to this
		  problem presented in previous works, in terms of walking
		  speed.},
  annote = {accepted},
  keywords = {RoboCup},
  mendeley-tags = {RoboCup},
  url = {http://homepages.stca.herts.ac.uk/~sv08aav/pub/lattarullo.vandijk.rc2011.alliance.pdf}
}

@inproceedings{dijk_what_2010,
  author = {van Dijk, Sander G. and Polani, Daniel and Nehaniv,
		  Chrystopher L.},
  title = {{What do You Want to do Today? Relevant-Information
		  Bookkeeping in Goal-Oriented Behaviour}},
  booktitle = {Artificial Life XII: The 12th International Conference on
		  the Synthesis and Simulation of Living Systems},
  year = {2010},
  editor = {Fellermann, Harold and D\"{o}rr, Mark and Hanczyc, Martin
		  and Ladegaard, Lone L. and Maurer, Sarah and Merkle, Daniel
		  and Monnard, Pierre-Alain and St\o y, Kasper and Rasmussen,
		  Steen},
  pages = {176--183},
  address = {Odense, Denmark},
  publisher = {MIT Press},
  abstract = {We extend existing models and methods for the
		  informational treatment of the perception-action loop to
		  the case of goal-oriented behaviour and introduce the
		  notion of \emph{relevant goal information} as the amount of
		  information an agent necessarily has to maintain about its
		  goal. Starting from the hypothesis that organisms use
		  information economically, we study the structure of this
		  information and how goal-information parsimony can guide
		  behaviour. It is shown how these methods lead to a general
		  definition and quantification of sub-goals and how the
		  biologically motivated hypothesis of information parsimony
		  gives rise to the emergence of behavioural properties such
		  as least-commitment and goal-concealing.},
  url = {http://homepages.stca.herts.ac.uk/~sv08aav/pub/vandijk.alife10.goal.pdf}
}

@inproceedings{dijk_hierarchical_2009,
  author = {van Dijk, Sander G. and Polani, Daniel and Nehaniv,
		  Chrystopher L.},
  title = {{Hierarchical Behaviours: Getting the Most Bang for your
		  Bit}},
  booktitle = {Proc. European Conference on Artificial Life 2009,
		  Budapest},
  year = {2009},
  address = {Budapest, Hungary},
  abstract = {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 of
		  hierarchical architectures on the required information
		  processing capability of an optimally acting agent. We show
		  that an information-theoretical approach provides important
		  insights into why factored and layered behaviour structures
		  are beneficial.},
  url = {http://homepages.stca.herts.ac.uk/~sv08aav/pub/vandijk.ecal09.hier.pdf}
}