This paper studies the problem of learning computable functions in the limit by extending Gold's inductive inference framework to incorporate \textit{computational observations} and \textit{restricted input sources}. Complimentary to the traditional Input-Output Observations, we introduce Time-Bound Observations, and Policy-Trajectory Observations to study the learnability of general recursive functions under more realistic constraints. While input-output observations do not suffice for learning the class of general recursive functions in the limit, we overcome this learning barrier by imposing computational complexity constraints or supplementing with approximate time-bound observations. Further, we build a formal framework around observations of \textit{computational agents} and show that learning computable functions from policy trajectories reduces to learning rational functions from input and output, thereby revealing interesting connections to finite-state transducer inference. On the negative side, we show that computable or polynomial-mass characteristic sets cannot exist for the class of linear-time computable functions even for policy-trajectory observations.

Planning is an extraordinary ability in which the brain imagines and then enacts evaluated possible futures. Using traditional planning models, computer scientists have attempted to replicate this capacity with some level of success but ultimately face a reoccurring limitation: as the plan grows in steps, the number of different possible futures makes it intractable to determine the right sequence of actions to reach a goal state. Based on prior theoretical work on how the ecology of an animal governs the value of spatial planning, we developed a more efficient biologically-inspired planning algorithm, TLPPO. This algorithm allows us to achieve mouselevel predator evasion performance with orders of magnitude less computation than a widespread algorithm for planning in the situations of partial observability that typify predator-prey interactions. We compared the performance of a real-time agent using TLPPO against the performance of live mice, all tasked with evading a robot predator. We anticipate these results will be helpful to planning algorithm users and developers, as well as to areas of neuroscience where robot-animal interaction can provide a useful approach to studying the basis of complex behaviors.

Artificial Intelligence: Foundations of Computational Agents [Poole, David L., Mackworth, Alan K.] on Amazon.com. *FREE* shipping on qualifying offers. Artificial Intelligence: Foundations of Computational Agents

This Python code is meant to demonstrate some of the algorithms in Artificial Intelligence: foundations of computational agents, second edition. This is not polished code. It is meant to code representations that work together. It will probably never be polished (or when it is polished it is probably time to throw it away and start again), and should no be relied on. We make no warranty of any kind, expressed or implied, with regard to these programs or the documentation.

Abduction is a form of reasoning where assumptions are made to explain observations. For example, if an agent were to observe that some light was not working, it can hypothesize what is happening in the world to explain why the light was not working. An intelligent tutoring system could try to explain why a student gives some answer in terms of what the student understands and does not understand. The term abduction was coined by Peirce (1839-1914) to differentiate this type of reasoning from deduction, which involves determining what logically follows from a set of axioms, and induction, which involves inferring general relationships from examples. In abduction, an agent hypothesizes what may be true about an observed case.

In this paper, we propose an AI-FML robotic agent for student learning behavior ontology construction which can be applied in English speaking and listening domain. The AI-FML robotic agent with the ontology contains the perception intelligence, computational intelligence, and cognition intelligence for analyzing student learning behavior. In addition, there are three intelligent agents, including a perception agent, a computational agent, and a cognition agent in the AI-FML robotic agent. We deploy the perception agent and the cognition agent on the robot Kebbi Air. Moreover, the computational agent with the Deep Neural Network (DNN) model is performed in the cloud and can communicate with the perception agent and cognition agent via the Internet. The proposed AI-FML robotic agent is applied in Taiwan and tested in Japan. The experimental results show that the agents can be utilized in the human and machine co-learning model for the future education.

The conference Robotics: Science and Systems was held at the University of Washington in Seattle, from June 28 to July 1, 2009. More than 300 international researchers attended this single-track conference to learn about the most exciting robotics research and most advanced robotic systems. The program committee selected 39 papers out of 154 submissions. The program also included invited talks. The plenary presentations were complemented by workshops.

This book is published by Cambridge University Press, 2010. The html is made available under a Creative Commons Attribution-Noncommercial-No Derivative Works 2.5 Canada License. We hope that you enjoy reading the book and that you get excited about the development of artificial intelligence.

A virtual-reality drama by University at Buffalo researchers -- aimed at transforming the movie-going experience -- is driving the development of increasingly "self-aware" computational agents that are able to improvise responses to the spontaneous actions of human users. These improvisational computer agents are expected to influence the development of electronic devices of tomorrow, making them much more user-friendly because they will be able to respond to the idiosyncratic needs of each user. The researchers' virtual-reality drama, The Trial The Trail, is a brand new type of dramatic entertainment, where instead of identifying with the protagonist, the audience becomes the protagonist. The multidisciplinary team formed two years ago when Josephine Anstey, assistant professor in the Department of Media Study in the UB College of Arts and Sciences, was looking for ways to make VR dramas more believable. At the same time, Stuart C. Shapiro, Ph.D., professor in the Department of Computer Science and Engineering in the UB School of Engineering and Applied Sciences, was seeking applications to challenge the computerized cognitive agent called CASSIE that he and his colleagues had developed.

In this paper we propose a research agenda on the use of information markets as tools to collect, aggregate and analyze citizens’ opinions, expectations and preferences from social media in order to support public policy design and implementation. We argue that markets are institutional settings able to efficiently allocate scarce resources, aggregate and disseminate information into prices and accommodate hedging against various types of risks. We discuss various types of information markets, as well as address the participation of both human and computational agents in such markets.