Poker Squares is a single-player card game played on a 5 x 5 grid, in which a player attempts to create as many high-scoring Poker hands as possible. As a stochastic single-player game with an extremely large state space, this game offers an interesting area of application for Monte-Carlo Tree Search (MCTS). This paper describes enhancements made to the MCTS algorithm to improve computer play, including pruning in the selection stage and a greedy simulation algorithm. These enhancements make extensive use of domain knowledge in the form of a state evaluation heuristic. Experimental results demonstrate both the general efficacy of these enhancements and their ideal parameter settings.

While Hierarchical Task Networks are frequently cited as flexible and powerful planning models, they are often ignored due to the intensive labor cost for experts/programmers, due to the need to create and refine the model by hand. While recent work has begun to address this issue by working towards learning aspects of an HTN model from demonstration, or even the whole framework, the focus so far has been on simple domains, which lack many of the challenges faced in the real world such as imperfect information and real-time environments. I plan to extend this work using the domain of real-time strategy (RTS) games, which have gained recent popularity as a challenging and complex domain for AI research.

Resource optimization and scheduling is a costly, challenging problem that affects almost every aspect of our lives. One example that affects each of us is health care: Poor systems design and scheduling of resources can lead to higher rates of patient noncompliance and burnout of health care providers, as highlighted by the Institute of Medicine (Brandenburg et al. 2015). In aerospace manufacturing, every minute re-scheduling in response to dynamic disruptions in the build process of a Boeing 747 can cost up to $100.000. The military is also highly invested in the effective use of resources. In missile defense, for example, operators must =solve a challenging weapon-to-target problem, balancing the cost of expendable, defensive weapons while hedging against uncertainty in adversaries’ tactics. Researchers in artificial intelligence (AI) planning and scheduling strive to develop algorithms to improve resource allocation. However, there are two primary challenges. First, optimal task allocation and sequencing with upper and lower-bound temporal constraints (i.e., deadlines and wait constraints) is NP-Hard (Bertsimas and Weismantel 2005). Approximation techniques for scheduling exist and typically rely on the algorithm designer crafting heuristics based on domain expertise to decompose or structure the scheduling problem and prioritize the manner in which resources are allocated and tasks are sequenced (Tang and Parker 2005; Jones, Dias, and Stentz 2011). The second problem is this aforementioned reliance on crafting clever heuristics based on domain knowledge. Manually capturing domain knowledge within a scheduling algorithm remains a challenging process and leaves much to be desired (Ryan et al. 2013). The aim of my thesis is to develop an autonomous system that 1) learns the heuristics and implicit rules-of-thumb developed by domain experts from years of experience, 2) embeds and leverages this knowledge within a scalable resource optimization framework, and 3) provides decision support in a way that engages users and benefits them in their decision-making process. By intelligently leveraging the ability of humans to learn heuristics and the speed of modern computation, we can improve the ability to coordinate resources in these time and safety-critical domains.

In many real-world domains, the presence of machines is becoming more ubiquitous to the point that they are usually more than simple automation tools. As part of the environment amongst human users, it is necessary for these computers and robots to be able to interact with them reasonably by either working independently around them or participating in a task, especially one with which a person needs help. This interactive procedure requires several steps: recognizing the user and environment from sensor data, interpreting the user’s activity and motives, determining a responsive behavior, performing the behavior, and then recognizing everything again to confirm the behavior choice and replan if necessary. At the moment, the research areas addressing these steps, activity recognition, plan recognition, intent recognition, and planning, have all been primarily studied independently. However, pipelining each independent process can be risky in real-time situations where there may be enough time to only run a few steps. This leads to a critical question: how do we perform everything under time constraints? In this thesis summary, I propose a framework that integrates these processes by taking advantage of features shared between them.

Planning in hybrid systems has been gaining research interest in the Artificial Intelligence community in recent years. Hybrid systems allow for a more accurate representation of real world problems, though solving them is very challenging due to complex system dynamics and a large model feature set. We developed DiNo, a new planner designed to tackle problems set in hybrid domains.DiNo is based on the discretise and validate approach and uses the novel Staged Relaxed Planning Graph+ (SRPG+) heuristic.

Multi-robot teams are useful in a variety of task allocation domains such as warehouse automation and surveillance. Robots in such domains perform tasks at given locations and specific times, and are allocated tasks to optimize given team objectives. We propose an efficient, satisficing and centralized Monte Carlo TreeSearch based algorithm exploiting branch and bound paradigm to solve the multi-robot task allocation problem with spatial, temporal and other side constraints. Unlike previous heuristics proposed for this problem, our approach offers theoretical guarantees and finds optimal solutions for some non-trivial data sets.

A critical challenge in temporal planning is robustly dealing with non-determinism introduced by the environment, e.g., the durational uncertainty of an action taken by a robot in the physical world due to slippage or other unexpected influences. Recent advances show that robustness, which accounts for uncertainty in predicting schedule success, is a better measure of solution quality than traditional metrics such as flexibility. This paper introduces the Robust Execution Problem (REP) for finding maximally robust dispatch strategies for general probabilistic temporal planning problems. While the REP is generally intractable in practice, we introduce approximate solution techniques—one that can be computed statically prior to the start of execution while providing robustness guarantees and one that dynamically adjusts to opportunities and setbacks during execution. We show empirically that dynamically optimizing for robustness improves the likelihood of execution success.

Profound knowledge about Artificial Intelligence (AI) will become increasingly important for careers in science and engineering. Therefore an innovative educational project teaching fundamental concepts of AI at high school level will be presented in this paper. We developed an AI-course covering major topics (problem solving, search, planning, graphs, datastructures, automata, agent systems, machine learning) which comprises both theoretical and hands-on components. A pilot project was conducted and empirically evaluated. Results of the evaluation show that the participating pupils have become familiar with those concepts and the various topics addressed. Results and lessons learned from this project form the basis for further projects in different schools which intend to integrate AI in future secondary science education.

This paper considers prescriptive evacuation planning for a region threatened by a natural disaster such a flood, a wildfire, or a hurricane. It proposes a Benders decomposition that generalizes the two-stage approach proposed in earlier work for convergent evacuation plans. Experimental results show that Benders decomposition provides significant improvements in solution quality in reasonable time: It finds provably optimal solutions to scenarios considered in prior work, closing these instances, and increases the number of evacuees by 10 to 15% on average on more complex flood scenarios.

The results of autonomy are often some mechanism Research on cognitive architectures have made significant by which we automate system behavior and decision-making contributions over the years including the ability to reason computationally. We claim that for a system to exhibit with multiple knowledge modes (Laird 2012), to introspectively self-regulated autonomy, however, it must have a model of examine the rationale for a decision (Forbus, Klenk itself in addition to the usual model of the world. Like selfregulated and Hinrichs 2009), and the ability to learn knowledge of learning (e.g., Bjork, Dunlosky and Kornell 2013), varied levels of abstraction (Langley and Choi 2006). Comparatively whereby a learner manages the pace, resources, and goals of less research efforts examine the metacognitive learning, self-regulated autonomy involves a system that contributions to effective decision-making and behavior.