The problem of optimal planning under uncertainty in collaborative multi-agent domains is known to be deeply intractable but still demands a solution. This thesis will explore principled approximation methods that yield tractable approaches to planning for AI assistants, which allow them to understand the intentions of humans and help them achieve their goals. AI assistants are ubiquitous in video games, mak- ing them attractive domains for applying these planning techniques. However, games are also challenging domains, typically having very large state spaces and long planning horizons. The approaches in this thesis will leverage recent advances in Monte-Carlo search, approximation of stochastic dynamics by deterministic dynamics, and hierarchical action representation, to handle domains that are too complex for existing state of the art planners. These planning techniques will be demonstrated across a range of video game domains.

Authoring narrative content for interactive digital media can be both difficult and time consuming.The research proposed here aims at enhancing the capabilities of content creators through the development of a computational model that improves the quality of automatically generated stories, potentially decreasing the burden placed on the author. The quality and believability of a story can be significantly enhanced by the presence of compelling characters. To achieve this objective, I aim to develop a choice-based computational model that facilitates the automatic generation of narrative that includes characters that are made more compelling by the presence of distinct personality characteristics.

Existing theoretical universal algorithmic intelligence models are not practically realizable. More pragmatic approach to artificial general intelligence is based on cognitive architectures, which are, however, non-universal in sense that they can construct and use models of the environment only from Turing-incomplete model spaces. We believe that the way to the real AGI consists in bridging the gap between these two approaches. This is possible if one considers cognitive functions as a "cognitive bias" (priors and search heuristics) that should be incorporated into the models of universal algorithmic intelligence without violating their universality. Earlier reported results suiting this approach and its overall feasibility are discussed on the example of perception, planning, knowledge representation, attention, theory of mind, language, and some others.

Domain-independent planning is one of the foundational areas in the field of Artificial Intelligence. A description of a planning task consists of an initial world state, a goal, and a set of actions for modifying the world state. The objective is to find a sequence of actions, that is, a plan, that transforms the initial world state into a goal state. In optimal planning, we are interested in finding not just a plan, but one of the cheapest plans. A prominent approach to optimal planning these days is heuristic state-space search, guided by admissible heuristic functions. Numerous admissible heuristics have been developed, each with its own strengths and weaknesses, and it is well known that there is no single "best'' heuristic for optimal planning in general. Thus, which heuristic to choose for a given planning task is a difficult question. This difficulty can be avoided by combining several heuristics, but that requires computing numerous heuristic estimates at each state, and the tradeoff between the time spent doing so and the time saved by the combined advantages of the different heuristics might be high. We present a novel method that reduces the cost of combining admissible heuristics for optimal planning, while maintaining its benefits. Using an idealized search space model, we formulate a decision rule for choosing the best heuristic to compute at each state. We then present an active online learning approach for learning a classifier with that decision rule as the target concept, and employ the learned classifier to decide which heuristic to compute at each state. We evaluate this technique empirically, and show that it substantially outperforms the standard method for combining several heuristics via their pointwise maximum.

The early classifications of the computational complexity of planning under various restrictions in STRIPS (Bylander) and SAS+ (Baeckstroem and Nebel) have influenced following research in planning in many ways. We go back and reanalyse their subclasses, but this time using the more modern tool of parameterized complexity analysis. This provides new results that together with the old results give a more detailed picture of the complexity landscape. We demonstrate separation results not possible with standard complexity theory, which contributes to explaining why certain cases of planning have seemed simpler in practice than theory has predicted. In particular, we show that certain restrictions of practical interest are tractable in the parameterized sense of the term, and that a simple heuristic is sufficient to make a well-known partial-order planner exploit this fact.

Planning is concerned with the automated solution of action sequencing problems described in declarative languages giving the action preconditions and effects. One important application area for such technology is the creation of new processes in Business Process Management (BPM), which is essential in an ever more dynamic business environment. A major obstacle for the application of Planning in this area lies in the modeling. Obtaining a suitable model to plan with -- ideally a description in PDDL, the most commonly used planning language -- is often prohibitively complicated and/or costly. Our core observation in this work is that this problem can be ameliorated by leveraging synergies with model-based software development. Our application at SAP, one of the leading vendors of enterprise software, demonstrates that even one-to-one model re-use is possible. The model in question is called Status and Action Management (SAM). It describes the behavior of Business Objects (BO), i.e., large-scale data structures, at a level of abstraction corresponding to the language of business experts. SAM covers more than 400 kinds of BOs, each of which is described in terms of a set of status variables and how their values are required for, and affected by, processing steps (actions) that are atomic from a business perspective. SAM was developed by SAP as part of a major model-based software engineering effort. We show herein that one can use this same model for planning, thus obtaining a BPM planning application that incurs no modeling overhead at all. We compile SAM into a variant of PDDL, and adapt an off-the-shelf planner to solve this kind of problem. Thanks to the resulting technology, business experts may create new processes simply by specifying the desired behavior in terms of status variable value changes: effectively, by describing the process in their own language.

A robot coexisting with humans must not only be able to successfully perform physical tasks, but must also be able to interact with humans in a socially appropriate manner. In many social settings, this involves the use of social signals like gaze, facial expression, and language. In this paper we discuss preliminary work focusing on the problem of combining social interaction with task-based action in a dynamic, multiagent bartending domain, using an embodied robot. We discuss how social states are inferred from low-level sensors, using vision and speech as input modalities, and present a planning approach that models task, dialogue, and social actions in a simple bartending scenario. This approach allows us to build interesting plans, which have been evaluated in a real-world study with human subjects, using a general purpose, off-the-shelf planner, as an alternative to more mainstream methods of interaction management.

Significant progress has been made in the area of multiagent path finding/planning in the past decade (Silver 2005; van den Berg et al. 2009; Standley 2010; Luna and Bekris 2011; Wang and Botea 2011). In this work, we introduce a multi-agent path planning problem similar to that of (Standley (a) (b) (c) 2010) and aim at maximizing parallelism among the agents. That is, we seek a feasible plan that minimizes the Figure 1: a) A simple graph G. b) A gadget for splitting time it takes the last agent to reach its goal. To solve the an undirected edge through time steps.

The Next-Generation Transportation program coordinates the evolution and transformation of the current air-traffic management (ATM) system for the National Airspace System (NAS). Currently the NAS has a limited capacity and cannot handle the increasing future air traffic demands. However, before newly proposed ATM concepts are deployed they must be rigorously evaluated under realistic conditions. This paper presents AGENTFLY, an emerging NAS-wide highfidelity multi-agent ATM simulator with precise emulation of the human controller operation workload model and human-system interaction. The simulator is validated using a flight scenario developed by the U.S. Federal Aviation Administration that is based on real data. We present preliminary results focusing on the accuracy of the simulated controllers within AGENTFLY.

The average home computer user needs help in reducing the security risk of their home computer. We are working on an alternative approach from current home security software in which a software agent helps a user manage his/her security risk. Planning is integral to the design of this agent in several ways. First, planning can be used to make the underlying security model manageable by generating attack paths to identify vulnerabilities that are not a problem for a particular user/home computer. Second, planning can be used to identify interventions that can either avoid the vulnerability or mitigate the damage should it occur. In both cases, a central capability is that of generating alternative plans so as to find as many possible ways to trigger the vulnerability and to provide the user with options should the obvious not be acceptable. We describe our security model and our state-based approach to generating alternative plans. We show that the state-based approach can generate more diverse plans than a heuristic-based approach. However, the state-based approach sometimes generates this diversity with better quality at higher search cost.