Boundaries and Topological Algorithms

This thesis develops a model for the topological structure of situations. In this model, the topological structure of space is altered by the presence or absence of boundaries, such as those at the edges of objects. This allows the intuitive meaning of topological concepts such as region connectivity, function continuity, and preservation of topological structure to be modeled using the standard mathematical definitions. The thesis shows that these concepts are important in a wide range of artificial intelligence problems, including low-level vision, high-level vision, natural language semantics, and high-level reasoning.

From Genetic Algorithms to Efficient Organization

The work described in this thesis began as an inquiry into the nature and use of optimization programs based on "genetic algorithms." That inquiry led, eventually, to three powerful heuristics that are broadly applicable in gradient-ascent programs: First, remember the locations of local maxima and restart the optimization program at a place distant from previously located local maxima. Second, adjust the size of probing steps to suit the local nature of the terrain, shrinking when probes do poorly and growing when probes do well. And third, keep track of the directions of recent successes, so as to probe preferentially in the direction of most rapid ascent. These algorithms lie at the core of a novel optimization program that illustrates the power to be had from deploying them together. The efficacy of this program is demonstrated on several test problems selected from a variety of fields, including De Jong's famous test-problem suite, the traveling salesman problem, the problem of coordinate registration for image guided surgery, the energy minimization problem for determining the shape of organic molecules, and the problem of assessing the structure of sedimentary deposits using seismic data.

The Architect's Collaborator: Toward Intelligent Tools for Conceptual Design

In early stages of architectural design, as in other design domains, the language used is often very abstract. In architectural design, for example, architects and their clients use experiential terms such as "private" or "open" to describe spaces. If we are to build programs that can help designers during this early-stage design, we must give those programs the capability to deal with concepts on the level of such abstractions. The work reported in this thesis sought to do that, focusing on two key questions: How are abstract terms such as "private" and "open" translated into physical form? How might one build a tool to assist designers with this process? The Architect's Collaborator (TAC) was built to explore these issues. It is a design assistant that supports iterative design refinement, and that represents and reasons about how experiential qualities are manifested in physical form. Given a starting design and a set of design goals, TAC explores the space of possible designs in search of solutions that satisfy the goals. It employs a strategy we've called dependency-directed redesign: it evaluates a design with respect to a set of goals, then uses an explanation of the evaluation to guide proposal and refinement of repair suggestions; it then carries out the repair suggestions to create new designs. A series of experiments was run to study TAC's behavior. Issues of control structure, goal set size, goal order, and modification operator capabilities were explored. In addition, TAC's use as a design assistant was studied in an experiment using a house in the process of being redesigned. TAC's use as an analysis tool was studied in an experiment using Frank Lloyd Wright's Prairie houses.

Using Analogy to Acquire Commonsense Knowledge from Human Contributors

The goal of the work reported here is to capture the commonsense knowledge of non-expert human contributors. Achieving this goal will enable more intelligent human-computer interfaces and pave the way for computers to reason about our world. In the domain of natural language processing, it will provide the world knowledge much needed for semantic processing of natural language. To acquire knowledge from contributors not trained in knowledge engineering, I take the following four steps: (i) develop a knowledge representation (KR) model for simple assertions in natural language, (ii) introduce cumulative analogy, a class of nearest-neighbor based analogical reasoning algorithms over this representation, (iii) argue that cumulative analogy is well suited for knowledge acquisition (KA) based on a theoretical analysis of effectiveness of KA with this approach, and (iv) test the KR model and the effectiveness of the cumulative analogy algorithms empirically. To investigate effectiveness of cumulative analogy for KA empirically, Learner, an open source system for KA by cumulative analogy has been implemented, deployed, and evaluated. (The site "1001 Questions," is available at http://teach-computers.org/learner.html). Learner acquires assertion-level knowledge by constructing shallow semantic analogies between a KA topic and its nearest neighbors and posing these analogies as natural language questions to human contributors. Suppose, for example, that based on the knowledge about "newspapers" already present in the knowledge base, Learner judges "newspaper" to be similar to "book" and "magazine." Further suppose that assertions "books contain information" and "magazines contain information" are also already in the knowledge base. Then Learner will use cumulative analogy from the similar topics to ask humans whether "newspapers contain information." Because similarity between topics is computed based on what is already known about them, Learner exhibits bootstrapping behavior --- the quality of its questions improves as it gathers more knowledge. By summing evidence for and against posing any given question, Learner also exhibits noise tolerance, limiting the effect of incorrect similarities. The KA power of shallow semantic analogy from nearest neighbors is one of the main findings of this thesis. I perform an analysis of commonsense knowledge collected by another research effort that did not rely on analogical reasoning and demonstrate that indeed there is sufficient amount of correlation in the knowledge base to motivate using cumulative analogy from nearest neighbors as a KA method. Empirically, evaluating the percentages of questions answered affirmatively, negatively and judged to be nonsensical in the cumulative analogy case compares favorably with the baseline, no-similarity case that relies on random objects rather than nearest neighbors. Of the questions generated by cumulative analogy, contributors answered 45% affirmatively, 28% negatively and marked 13% as nonsensical; in the control, no-similarity case 8% of questions were answered affirmatively, 60% negatively and 26% were marked as nonsensical.

Reinforcement Learning by Policy Search

One objective of artificial intelligence is to model the behavior of an intelligent agent interacting with its environment. The environment's transformations can be modeled as a Markov chain, whose state is partially observable to the agent and affected by its actions; such processes are known as partially observable Markov decision processes (POMDPs). While the environment's dynamics are assumed to obey certain rules, the agent does not know them and must learn. In this dissertation we focus on the agent's adaptation as captured by the reinforcement learning framework. This means learning a policy---a mapping of observations into actions---based on feedback from the environment. The learning can be viewed as browsing a set of policies while evaluating them by trial through interaction with the environment. The set of policies is constrained by the architecture of the agent's controller. POMDPs require a controller to have a memory. We investigate controllers with memory, including controllers with external memory, finite state controllers and distributed controllers for multi-agent systems. For these various controllers we work out the details of the algorithms which learn by ascending the gradient of expected cumulative reinforcement. Building on statistical learning theory and experiment design theory, a policy evaluation algorithm is developed for the case of experience re-use. We address the question of sufficient experience for uniform convergence of policy evaluation and obtain sample complexity bounds for various estimators. Finally, we demonstrate the performance of the proposed algorithms on several domains, the most complex of which is simulated adaptive packet routing in a telecommunication network.

Information Dissemination and Aggregation in Asset Markets with Simple Intelligent Traders

Various studies of asset markets have shown that traders are capable of learning and transmitting information through prices in many situations. In this paper we replace human traders with intelligent software agents in a series of simulated markets. Using these simple learning agents, we are able to replicate several features of the experiments with human subjects, regarding (1) dissemination of information from informed to uninformed traders, and (2) aggregation of information spread over different traders.

On the Convergence of Stochastic Iterative Dynamic Programming Algorithms

Recent developments in the area of reinforcement learning have yielded a number of new algorithms for the prediction and control of Markovian environments. These algorithms, including the TD(lambda) algorithm of Sutton (1988) and the Q-learning algorithm of Watkins (1989), can be motivated heuristically as approximations to dynamic programming (DP). In this paper we provide a rigorous proof of convergence of these DP-based learning algorithms by relating them to the powerful techniques of stochastic approximation theory via a new convergence theorem. The theorem establishes a general class of convergent algorithms to which both TD(lambda) and Q-learning belong.

Interaction and Intelligent Behavior

We introduce basic behaviors as primitives for control and learning in situated, embodied agents interacting in complex domains. We propose methods for selecting, formally specifying, algorithmically implementing, empirically evaluating, and combining behaviors from a basic set. We also introduce a general methodology for automatically constructing higher--level behaviors by learning to select from this set. Based on a formulation of reinforcement learning using conditions, behaviors, and shaped reinforcement, out approach makes behavior selection learnable in noisy, uncertain environments with stochastic dynamics. All described ideas are validated with groups of up to 20 mobile robots performing safe--wandering, following, aggregation, dispersion, homing, flocking, foraging, and learning to forage.

Scaling algorithms for distributed max flow

Bibliography: p. 22-24.