One challenge for cognitive architectures is to effectively use different forms of knowledge and learning. We present a case study of Soar agents that play a multiplayer dice game, in which probabilistic reasoning and heuristic symbolic knowledge appear to play a central role. We develop and evaluate a collection of agents that use different combinations of probabilistic decision making, heuristic symbolic reasoning, opponent modeling, and learning. We demonstrate agents that use Soar’s rule learning mechanism (chunking) to convert deliberate reasoning with probabilities into implicit reasoning, and then use reinforcement learning to further tune performance.

In most cognitive architectures, episodic memory is either not implemented, or plays a secondary role. In contrast, in the Xapagy architecture episodic memory is the primary means of acquiring and using knowledge. Shadowing, the main reasoning method of the system, relies on unprocessed historical recordings of concrete events to determine the agent's behavior. This paper outlines the use of episodic memory in Xapagy, and investigates whether episodic memory might play a wider role in cognitive architectures at large.

Desiderata for cognitive architectures that are to support the extent of human-level intelligence required in virtual humans imply the need to bridge a range of dichotomies faced by such architectures. The focus here is first on two general approaches to building such bridges — addition and reduction — and then on a pair of general tools – graphical models and piecewise continuous functions — that exploit the second approach towards developing such an architecture. Evaluation is in terms of the architecture’s demonstrated ability and future potential for bridging the dichotomies.

I ask why humans are smarter than other primates, and I hypothesize that an important part of the answer lies in what I call the Strong Story Hypothesis, which holds that story telling and understanding have a central role in human intelligence. Next, I introduce another hypothesis, the Driven Perception Hypothesis, which holds that we derive much of our commonsense, including the commonsense required in story understanding, by deploying our perceptual apparatus on real and imagined events. Then, after discussing methodology, I describe the representations and methods embodied in the Genesis system, a story-understanding system that analyzes stories ranging from precis of Shakespeare's plots to descriptions of conflicts in cyberspace. The Genesis system works with short story summaries, provided in English, together with low-level commonsense rules and higher-level reflection patterns, likewise expressed in English. Using only a small collection of commonsense rules and reflection patterns, Genesis demonstrates several story-understanding capabilities, such as determining that both Macbeth and the 2007 Russia-Estonia Cyberwar involve revenge, even though neither the word revenge nor any of its synonyms are mentioned. Finally, I describe Rao's Visio-Spatial Reasoning System, a system that recognizes activities such as approaching, jumping, and giving, and answers commonsense questions posed by Genesis.

The paper provides an investigation and identification of the values and assumptions that influence the applications and results derived from the applications of game theoretical models to solve logistical problems. The ultimate goal is to identify and begin to eliminate prejudices and blind spots within the formulation of the game theory constraints and the application itself. We explore the investigation and identification of blind spots through the application of game theoretical models to solve problems concerning resource allocation. In particular, the paper investigates the application of game theoretical models to allocate resources in crisis situations.

Simulation techniques have long sustained research in various domains of physical, biological, and social sciences. Currently, humanists are exploring the usefulness of simulations for addressing various research questions. The nature and challenges of this enterprise are presented here in respect to collaborative work, the relation of humanities to the sciences, the transformative nature of digital methods of research within the humanities. This article describes a coordinated attempt to pursue these issues via a Summer Institute funded by the National Endowment for the Humanities, and briefly notes the projects of three of the Institute’s participants. Their work is described in detail elsewhere within this volume.

One approach to bridging the historic divide between "symbolic" and "subsymbolic" AI is to incorporate a subsymbolic system and a symbolic system into a synergetic integrative cognitive architecture. Here we consider various issues related to incorporating (subsymbolic) compositional spatiotemporal deep learning networks (CSDLNs, a term introduced to denote the category including HTM, DeSTIN and other similar systems) into an integrative cognitive architecture including symbolic aspects. The core conclusion is that for such integration to be meaningful, it must involve dynamic and adaptive linkage and conversion between CSDLN attractors spanning sensory, motor and goal hierarchies, and analogous representations in the remainder of the integrative architecture. We suggest the mechanism of "semantic CSDLNs", which maintain the general structure of CSDLNs but contain more abstract patterns, similar to those represented in more explicitly symbolic AI systems. This notion is made concrete by describing a planned integration of the DeSTIN CSDLN into the OpenCog integrative cognitive system (which includes a probabilistic-logical symbolic component).

Language processing architectures today are rarely designed to provide psychologically plausible accounts of their representations and algorithms. Engineering decisions dominate. This has led to words being seen as an incidental part of the architecture: the repository of all of language’s idiosyncratic aspects. Drawing on a body of past and ongoing research by myself and others I have concluded that this view of words is wrong. Words are actually present at the most abstract, pre-linguistic levels of the NLP architecture and that there are phenomena in language use that are best accounted for by assuming that concepts are words.

Shared Mental Models (SSM) are crucial for adequate coordination of activities and resource deployment in disaster responses. Both human and robot are actors in the construction of such models. Based on a situated Cognitive Engineering (sCE) methodology, we identified the needs, functions and evaluation paradigm for this model construction support. Via prototyping, some basic functions proved to be of value (e.g., hierarchical view on functions, processes and resources). Currently, more advanced functions are under investigation (e.g., observability display). The evaluations will provide the empirical foundation of the underlying SMM theory for human-robot teams.

In this paper we address the design of robots that can be successful partners to humans in joint activity. The paper outlines an approach to achieving adjustable autonomy during execution- and hence to achieve resilient multi-actor joint action - based on both temporal and epistemic situation projection. The approach is based on non-deterministic planning techniques based on the situations calculus.