oacute; n

IJCAI Conference 2016 Conference Paper

Controllable Procedural Content Generation via Constrained Multi-Dimensional Markov Chain Sampling

• Sam Snodgrass
• Santiago Onta
• ntilde;
• oacute; n

Statistical models, such as Markov chains, have recently started to be studied for the purpose of Procedural Content Generation (PCG). A major problem with this approach is controlling the sampling process in order to obtain output satisfying some desired constraints. In this paper we present three approaches to constraining the content generated using multi-dimensional Markov chains: (1) a generate and test approach that simply resamples the content until the desired constraints are satisfied, (2) an approach that finds and resamples parts of the generated content that violate the constraints, and (3) an incremental method that checks for constraint violations during sampling. We test our approaches by generating maps for two classic video games, Super Mario Bros. and Kid Icarus.

IJCAI Conference 2015 Conference Paper

Pseudo-Supervised Training Improves Unsupervised Melody Segmentation

• Stefan Lattner
• Carlos Eduardo Cancino Chac
• oacute; n
• Maarten Grachten

An important aspect of music perception in humans is the ability to segment streams of musical events into structural units such as motifs and phrases. A promising approach to the computational modeling of music segmentation employs the statistical and information-theoretic properties of musical data, based on the hypothesis that these properties can (at least partly) account for music segmentation in humans. Prior work has shown that in particular the information content of music events, as estimated from a generative probabilistic model of those events, is a good indicator for segment boundaries. In this paper we demonstrate that, remarkably, a substantial increase in segmentation accuracy can be obtained by not using information content estimates directly, but rather in a bootstrapping fashion. More specifically, we use information content estimates computed from a generative model of the data as a target for a feed-forward neural network that is trained to estimate the information content directly from the data. We hypothesize that the improved segmentation accuracy of this bootstrapping approach may be evidence that the generative model provides noisy estimates of the information content, which are smoothed by the feed-forward neural network, yielding more accurate information content estimates.

IJCAI Conference 2011 Conference Paper

On the Role of Domain Knowledge in Analogy-Based Story Generation

• Santiago Onta
• ntilde;
• oacute; n
• Jichen Zhu

Computational narrative is a complex and interesting domain for exploring AI techniques that algorithmically analyze, understand, and most importantly, generate stories. This paper studies the importance of domain knowledge in story generation, and particularly in analogy-based story generation (ASG). Based on the construct of knowledge container in case-based reasoning, we present a theoretical framework for incorporating domain knowledge in ASG. We complement the framework with empirical results in our existing system Riu.

AAMAS Conference 2008 Conference Paper

An Agent Adaptive Model for Self-Organizing Multi-Agent Systems

• Candelaria Sansores
• Juan Pav
• oacute; n

Self-organizing multi-agent systems (MAS) use different mechanisms to mimic the adaptation exhibited by complex systems situated in unpredictable and dynamic environments. These mechanisms allow a collection of agents to spontaneously adapt their behavior towards an optimal organization. This paper presents a self-organization approach that exploits several selforganizing principles through an agent adaptive architecture and a reinforcement mechanism. This mechanism was designed and implemented using the INGENIAS methodology.

AAMAS Conference 2008 Conference Paper

INGENIAS Development Kit: a visual multi-agent system development environment

• JORGE J. GOMEZ-SANZ
• Rub
• eacute; n Fuentes
• Juan Pav
• oacute; n
• Ivan Garc
• iacute; a-Magarino

IJCAI Conference 2007 Conference Paper

• Santi Onta
• ntilde;
• oacute; n
• Enric Plaza

We present a proactive communication approach that allows CBR agents to gauge the strengths and weaknesses of other CBR agents. The communication protocol allows CBR agents to learn from communicating with other CBR agents in such a way that each agent is able to retain certain cases provided by other agents that are able to improve their individual performance (without need to disclose all the contents of each case base). The selection and retention of cases is modeled as a case bartering process, where each individual CBR agent autonomously decides which cases offers for bartering and which offered barters accepts. Experimental evaluations show that the sum of all these individual decisions result in a clear improvement in individual CBR agent performance with only a moderate increase of individual case bases.

IJCAI Conference 2007 Conference Paper

• Carlos Grand
• oacute; n
• Gilles Chabert
• Bertrand Neveu

This paper deals with systems of parametric equations over the reals, in the framework of interval constraint programming. As parameters vary within intervals, the solution set of a problem may have a non null volume. In these cases, an inner box (i. e. , a box included in the solution set) instead of a single punctual solution is of particular interest, because it gives greater freedom for choosing a solution. Our approach is able to build an inner box for the problem starting with a single point solution, by consistently extending the domain of every variable. The key point is a new method called generalized projection.