0000000000146812
AUTHOR
Daniel Polani
Order Parameters for Self-Organizing Maps
We introduce and discuss different approaches to construct order parameters for Kohonen’s Self-Organizing Maps. As one approach the notion of an order parameter in the sense of Haken’s synergetics is studied and contrasted with organization measures using SOM structure information.
On the Optimization of Self-Organizing Maps by Genetic Algorithms
Publisher Summary This chapter reviews the research on the genetic optimization of self-organizing maps (SOMs). The optimization of learning rule parameters and of initial weights is able to improve network performance. The latter, however, requires chromosome sizes proportional to the size of the SOM and becomes unwieldy for large networks. The optimization of learning rule structures leads to self-organization processes of character similar to the standard learning rule. A particularly strong potential lies in the optimization of SOM topologies, which allows the study of global dynamical properties of SOMs and related models, as well as to develop tools for their analysis. Hierarchies of …
Learning competitive pricing strategies by multi-agent reinforcement learning
Abstract In electronic marketplaces automated and dynamic pricing is becoming increasingly popular. Agents that perform this task can improve themselves by learning from past observations, possibly using reinforcement learning techniques. Co-learning of several adaptive agents against each other may lead to unforeseen results and increasingly dynamic behavior of the market. In this article we shed some light on price developments arising from a simple price adaptation strategy. Furthermore, we examine several adaptive pricing strategies and their learning behavior in a co-learning scenario with different levels of competition. Q-learning manages to learn best-reply strategies well, but is e…
A virtual testbed for analysis and design of sensorimotoric aspects of agent control
Abstract In this paper XRaptor is introduced, an object-oriented simulation tool. It provides a virtual multi-agent world which acts as testbed for agent control mechanisms. This environment encompasses a 3-dimensional space, in which the agents may move. Currently agents are realized modelling some abstract properties of flies and bats. XRaptor provides different levels of information flow and world manipulation capabilities from the agents' point of view. A further purpose of XRaptor is educational: Different teams of developers may design control units for agents which can then be subjected to a tournament.
Expanding the Active Inference Landscape: More Intrinsic Motivations in the Perception-Action Loop
Active inference is an ambitious theory that treats perception, inference and action selection of autonomous agents under the heading of a single principle. It suggests biologically plausible explanations for many cognitive phenomena, including consciousness. In active inference, action selection is driven by an objective function that evaluates possible future actions with respect to current, inferred beliefs about the world. Active inference at its core is independent from extrinsic rewards, resulting in a high level of robustness across e.g.\ different environments or agent morphologies. In the literature, paradigms that share this independence have been summarised under the notion of in…
Sequential Learning with LS-SVM for Large-Scale Data Sets
We present a subspace-based variant of LS-SVMs (i.e. regularization networks) that sequentially processes the data and is hence especially suited for online learning tasks. The algorithm works by selecting from the data set a small subset of basis functions that is subsequently used to approximate the full kernel on arbitrary points. This subset is identified online from the data stream. We improve upon existing approaches (esp. the kernel recursive least squares algorithm) by proposing a new, supervised criterion for the selection of the relevant basis functions that takes into account the approximation error incurred from approximating the kernel as well as the reduction of the cost in th…
Guest editors' introduction: special issue on sensor evolution.
Artificial life researchers, in their attempts to create life-as-it-could-be, have widely studied both the behavior of animals and artifacts. Early precursors of life-like artificial systems such as Grey Walter’s tortoises [4] or Valentino Braitenberg’s vehicles [1] were already demonstrating that ALife research is strongly motivated by the desire to understand and create life-like behavior and (neural) control. Creating life-like behavior in simulations or robots has increased our understanding of the design and evolution of controllers for artificial systems. Despite the interrelationship between behavior, sensors, and other morphological characteristics of animal systems, the evolution o…
On a Quantitative Measure for Modularity Based on Information Theory
The concept of modularity appears to be crucial for many questions in the field of Artificial Life research. However, there have not been many quantitative measures for modularity that are both general and viable. In this paper we introduce a measure for modularity based on information theory. Due to the generality of the information theory formalism, this measure can be applied to various problems and models; some connections to other formalisms are presented.
Behavior Classification with Self-Organizing Maps
We describe a method that applies Self-Organizing Maps for direct clustering of spatio-temporal data. We use the method to evaluate the behavior of RoboCup players. By training the Self-Organizing Map with player data we have the possibility to identify various clusters representing typical agent behavior patterns. Thus we can draw certain conclusions about their tactical behavior, using purely motion data, i.e. logfile information. In addition, we examine the player-ball interaction that give information about the players' technical capabilities.
Mainz Rolling Brains
Our agent team is the result of a development which had to take place under tight time limitations. The total development time available was slightly less than three months where over most of the time the team developers could invest no more than a few hours per week. The code was developed from scratch to improve over the design and quality of last year’s code. Thus one of the challenges was to keep a smooth development line and to avoid dead ends in the development, as well as to maintain a development environment in which a larger number of developers could work productively.
A Direct Approach to Robot Soccer Agents: Description for the Team Mainz Rolling rains Simulation League of RoboCup ’98
In the team described in this paper we realize a direct approach to soccer agents for the simulation league of the RoboCup '98- tournament. Its backbone is formed by a detailed world model. Based on information which is reconstructed on the world model level, the rule-based decision levels chose a relevant action. The architecture for the goalie is different from the regular players, introducing heterogeneousness into the team, which combines the advantages of the different control strategies.
A Study of the Simulated Evolution of the Spectral Sensitivity of Visual Agent Receptors
In this article we study a model for the evolution of the spectral sensitivity of visual receptors for agents in a continuous virtual environment. The model uses a genetic algorithm (GA) to evolve the agent sensors along with the control of the agents by requiring the agents to solve certain tasks in the simulation environment. The properties of the evolved sensors are analyzed for different scenarios. In particular, it is shown that the GA is able to find a balance between sensor costs and agent performance in such a way that the spectral sensor sensitivity reflects the emission spectrum of the target objects and that the capability of the sensors to evolve can help the agents significantl…
Kernelizing LSPE(λ)
We propose the use of kernel-based methods as underlying function approximator in the least-squares based policy evaluation framework of LSPE(λ) and LSTD(λ). In particular we present the 'kernelization' of model-free LSPE(λ). The 'kernelization' is computationally made possible by using the subset of regressors approximation, which approximates the kernel using a vastly reduced number of basis functions. The core of our proposed solution is an efficient recursive implementation with automatic supervised selection of the relevant basis functions. The LSPE method is well-suited for optimistic policy iteration and can thus be used in the context of online reinforcement learning. We use the hig…