Dave Gomboc

Tuning evaluation functions by maximizing concordance

Abstract Heuristic search effectiveness depends directly upon the quality of heuristic evaluations of states in a search space. Given the large amount of research effort devoted to computer chess throughout the past half-century, insufficient attention has been paid to the issue of determining if a proposed change to an evaluation function is beneficial. We argue that the mapping of an evaluation function from chess positions to heuristic values is of ordinal, but not interval scale. We identify a robust metric suitable for assessing the quality of an evaluation function, and present a novel method for computing this metric efficiently. Finally, we apply an empirical gradient-ascent procedure, also of our design, over this metric to optimize feature weights for the evaluation function of a computer-chess program. Our experiments demonstrate that evaluation function weights tuned in this manner give equivalent performance to hand-tuned weights.

Feedback Specificity and the Learning of Intercultural Communication Skills

The role of explicit feedback in learning has been studied from a variety of perspectives and in many contexts. In this paper, we examine the impact of the specificity of feedback delivered by an intelligent tutoring system in a game-based environment for cultural learning. We compared two versions: one that provided only “bottom-out” hints and feedback versus one that provided only conceptual messages. We measured during-training performance, in-game transfer, and long-term retention. Consistent with our hypotheses, specific feedback utterances produced inferior learning on the in-game transfer task when compared to conceptual utterances. No differences were found on a web-based post-test. We discuss possible explanations for these findings, particularly as they relate to the learning of loosely defined skills and serious games.

Developing INOTS to support interpersonal skills practice

The Immersive Naval Officer Training System (INOTS) is a blended learning environment that merges traditional classroom instruction with a mixed reality training setting. INOTS supports the instruction, practice and assessment of interpersonal communication skills. The goal of INOTS is to provide a consistent training experience to supplement interpersonal skills instruction for Naval officer candidates without sacrificing trainee throughput and instructor control. We developed an instructional design from cognitive task analysis interviews with experts to serve as a framework for system development. We also leveraged commercial student response technology and research technologies including natural language recognition, virtual humans, realistic graphics, intelligent tutoring and automated instructor support tools. In this paper, we describe our methodologies for developing a blended learning environment, and our challenges adding mixed reality and virtual human technologies to a traditional classroom to support interpersonal skills training.1 2

EVALUATION FUNCTION TUNING VIA ORDINAL CORRELATION

Heuristic search effectiveness depends directly upon the quality of heuristic evaluations of states in the search space. We show why ordinal correlation is relevant to heuristic search, present a metric for assessing the quality of a static evaluation function, and apply it to learn feature weights for a computer chess program.

Reflective tutoring for immersive simulation

Reflection is critically important for time-constrained training simulations that do not permit extensive tutor-student interactions during an exercise. Here, we describe a reflective tutoring system for a virtual human simulation of negotiation. The tutor helps students review their exercise, elicits where and how they could have done better, and uses explainable artificial intelligence (XAI) to allow students the chance to ask questions about the virtual humans behavior.

A Case Study of Improving Memory Locality in Polygonal Model Simplification: Metrics and Performance

Polygonal model simplification algorithms take a full-sized polygonal model as input and output a less-detailed version of the model with fewer polygons. When the internal data structures for the input model are larger than main memory, many simplification algorithms suffer from poor performance due to paging.We present a case study of the recently-introduced R-Simp algorithm and how its data locality and performance can be substantially improved through an off-line spatial sort and an on-line reorganization of its internal data structures. When both techniques are used, R-Simps performance improves by up to 7-fold. We empirically characterize the data-access pattern of R-Simp and present an application-specific metric, called cluster pagespan, of R-Simps locality of memory reference.