Now showing items 1-6 of 6
Improving Learning for Embodied Agents in Dynamic--Environments by State Factorisation
A new reinforcement learning algorithm designed--specifically for robots and embodied systems--is described. Conventional reinforcement learning methods intended for learning general tasks suffer from a number of disadvantages ...
Information Trade-Offs and the Evolution of Sensory Layout
In nature, sensors evolve to capture relevant information needed for organisms of a particular species to survive and reproduce. In this paper we study how sensor layouts may evolve in different environments and under ...
Organization of the information flow in the perception-action loop of evolved agents
Sensor evolution in nature aims at improving the acquisition of information from the environment and is intimately related with selection pressure towards adaptivity and robustness. Recent work in the area aims at studying ...
Sensory Channel Group and Structure from Uninterpreted Sensor Data
In this paper we focus on the problem of making a model of the sensory apparatus from raw uninterpreted sensory data as defined by Pierce and Kuipers (Artificial Intelligence 92:169-227, 1997). The method relies on generic ...
Tracking Information Flow through the Environment: Simple Cases of Stigmerg
(MIT Press, 2004)
Recent work in sensor evolution aims at studying the perception-action loop in a formalized information-theoretic manner. By treating sensors as extracting information and actuators as having the capability to "imprint" ...