No abstract

Biological brains can adapt and learn from past experience. Yet neuroevolution, that is, automatically creating artificial neural networks (ANNs) through evolutionary algorithms, has sometimes focused on static ANNs that cannot change their weights during their lifetime. A profound problem with evolving adaptive systems is that learning to learn is highly deceptive. Because it is easier at first to improve fitness without evolving the ability to learn, evolution is likely to exploit domain-dependent static (i.e., nonadaptive) heuristics. This article analyzes this inherent deceptiveness in a variety of different dynamic, reward-based learning tasks, and proposes a way to escape the deceptive trap of static policies based on the novelty search algorithm. The main idea in novelty search is to abandon objective-based fitness and instead simply search only for novel behavior, which avoids deception entirely. A series of experiments and an in-depth analysis show how behaviors that could potentially serve as a stepping stone to finding adaptive solutions are discovered by novelty search yet are missed by fitness-based search. The conclusion is that novelty search has the potential to foster the emergence of adaptive behavior in reward-based learning tasks, thereby opening a new direction for research in evolving plastic ANNs.

A major goal for researchers in neuroevolution is to evolve artificial neural networks (ANNs) that can learn during their lifetime. Such networks can adapt to changes in their environment that evolution on its own cannot anticipate. However, a profound problem with evolving adaptive systems is that if the impact of learning on the fitness of the agent is only marginal, then evolution is likely to produce individuals that do not exhibit the desired adaptive behavior. Instead, because it is easier at first to improve fitness without evolving the ability to learn, they are likely to exploit domaindependent static (i.e. non-adaptive) heuristics. This paper proposes a way to escape the deceptive trap of static policies based on the novelty search algorithm, which opens up a new avenue in the evolution of adaptive systems because it can exploit the behavioral difference between learning and nonlearning individuals. The main idea in novelty search is to abandon objective-based fitness and instead simply search only for novel behavior, which avoids deception entirely and has shown prior promising results in other domains. This paper shows that novelty search significantly outperforms fitness-based search in a tunably deceptive T-Maze navigation domain because it fosters the emergence of adaptive behavior.

No abstract

Research in learning analytics and educational data mining has recently become prominent in the fields of computer science and education. Most scholars in the field emphasize student learning and student data analytics; however, it is also important to focus on teaching analytics and teacher

No abstract

BACKGROUND Research suggests that adolescents can use peer resistance skills to avoid being pressured into risky behavior, such as early sexual behavior. Avatar-based Virtual Reality (AVR) technology offers a novel way to build these skills. OBJECTIVES Study aims were to: evaluate the feasibility of an AVR peer resistance skill building game (DRAMA-RAMA™); explore the impact of game play on peer resistance self-efficacy; and assess how positively the game was perceived. METHOD 45 low income early adolescent Hispanic girls were randomly assigned to either the intervention (DRAMA-RAMA™) or comparison game (Wii Dancing with the Stars™ [Wii DWTS™]) condition. All participants were offered a 5 session curriculum that included peer resistance skill content before playing their respective game for 15 minutes, once a week, for two weeks. Participants completed electronic surveys assessing demographics, peer resistance self-efficacy, and sexual behavior at baseline, after game play, and at 2 months. They also completed a paper-pencil game experience questionnaire immediately after playing their game. Data were analyzed using descriptive statistics, chi-square, and analyses of covariance. RESULTS The separate analyses of covariance showed a significant game effect at post-test for the peer resistance self-efficacy measure (F = 4.21, p < 0.05), but not at follow-up (F = 0.01, p = 0.92). DRAMA-RAMA™ was rated as positively as the Wii DWTS™ (p ≥ .26). DISCUSSION This randomized control trial provides initial support for the hypothesis that playing an AVR technology game can strengthen peer resistance skills, and early adolescent Hispanic girls will have a positive response to this game.

S imulating physically realistic complex fluid behaviors in a distributed interactive simulation (DIS) presents a challenging problem for computer graphics researchers. Such behaviors include driving boats through water, stirring liquids, blending differently colored fluids, mixing insolubles such as oil and water, rain falling and flowing on a terrain, and fluids interacting. These capabilities are useful in computer art, advertising, education, entertainment, and training. DIS denotes a broad field of simulation research and technology as well as a specific architectural approach, represented by the DIS communications protocol. 1 In this article we use the acronym DIS to designate any simulation conducted by distributed computation whose outputs must respond to changed inputs with the same timeliness the modeled system would exhibit. Modeling and animating fluids have captured the attention of many graphics researchers. However, no one has achieved general fluid models that are physically realistic and computationally efficient for real-time animation.