Illegal extraction of forest resources is fought, in many developing countries, by patrols through the forest that seek to deter such activity by decreasing its profitability. With limited resources for performing such patrols, a patrol strategy will seek to distribute the patrols throughout the forest, in space and time, in order to minimize the resulting amount of extraction that occurs or maximize the degree of forest protection, according to one of several potential metrics. We pose this problem as a Stackelberg game. We adopt and extend the simple, geometrically elegant model of (Albers 2010). First, we study optimal allocations of patrol density under generalizations of this model, relaxing several of its assumptions. Second, we pose the problem of generating actual schedules whose site visit frequencies are consistent with the analytically computed optimal patrol densities.

Computational social science, as with all complex adaptive systems sciences, involves a great amount of uncertainty on several fronts, including intrinsic arbitrariness such as that due to path dependence, disagreement on social theory and how to capture it in software, input data of different credibility that does not exactly match the requirements of software because it was gathered for another purpose, and inexactly matching translations between models that were designed for different purposes than the study at hand. This paper presents a method of formally tracking that uncertainty, keeping the data input parameters proportionate with logical and probabilistic constraints, and capturing proportionate dynamics of the output ordered by the decision points of policy change, for the purpose of risk-based analysis. Once ordered this way, the data can be compared to other data similarly expressed, whether that data is from simulation excursions or from the real world, for objective comparison and distance scoring at the level of dynamic patterns as opposed to single outcome validation. This method enables wargame adjudicators to be run out with data gleaned from the wargame, enables data to be repurposed for both training and testing set, and facilitates objective validation scoring through soft matching. Artificial intelligence tools used in the method include probabilistic ontologies with crisp and Bayesian inference, game trees that are multiplayer non-zero sum and decision point based rather than turn-based, and Markov processes to represent the dynamic data and align the models for objective comparison.

This paper surveys research in robotics in the AAMAS (Au- tonomous Agents and Multi-Agent Systems) community. It argues that the autonomous agents community can, and has, impact on robotics. Moreover, it argues that agents re- searchers should proactively seek to impact the robotics com- munity, to prevent independent re-discovery of known results, and to benefit autonomous agents science. To support these claims, I provide evidence from my own research into multi- robot teams, and from others’.

Reinforcement Learning (RL) is a paradigm for learning decision-making tasks that could enable robots to learn and adapt to situations on-line. For an RL algorithm to be practical for robotic control tasks, it must learn in very few samples, while continually taking actions in real-time. In addition, the algorithm must learn efficiently in the face of noise, sensor/actuator delays and continuous state features. In this paper, we describe TEXPLORE, a model-based RL method that addresses these issues. It learns a random forest model of the domain which generalizes dynamics to unseen states. The agent targets exploration on states that are both promising for the final policy and uncertain in the model. With sample-based planning and a novel parallel architecture, TEXPLORE can select actions continually in real-time whenever necessary. We empirically evaluate TEXPLORE learning to control the velocity of an autonomous vehicle in real-time.

The paper discusses how a human-robot team can remain “cohesive” while performing under stress. By cohesive the paper understands the ability of the team to operate effectively, with individual members being interdependent-yet-autonomous in carrying out tasks. For a human-robot team, we argue that this requires robots to (1) have an adequate sense of that interde- pendency in terms of the social dynamics within the team, and to (2) maintain transparency towards the human team members in terms of what it is doing, why, and to what extent it can achieve its (possibly jointly agreed upon) goals. The paper re- ports of recent field experience showing that failure in trans- parency results in reduced acceptability of robot autonomous behavior by the human team members. This reduction in acceptability can have two negative impacts on cohesiveness: Humans and robots fail to maintain common ground, and as a result they fail to maintain trust.

Hybrid group autonomy, organizations and teams composed of humans, machines and robots, are important to AI. Unlike the war in Iraq in 2002, the war in Afghanistan has hundreds of mobile robots aloft, on land, or under the sea. But when it comes to solving problems as part of a team, these agents are socially passive. Were the problem of aggregation and the autonomy of hybrids to be solved, robot teams could accompa- ny humans to address and solve problems together on Mars, under the sea, or in dan- gerous locations on earth (such as, fire-fighting, reactor meltdowns, and future wars). “Robot autonomy is required because one soldier cannot control several robots ... [and] because no computational system can discriminate between combatants and innocents in a close-contact encounter.” (Sharkey, 2008) Yet, today, one of the fundamental unsolved problems in the social sciences is the aggregation of individual data (such as preferences) into group (team) data (Giles, 2011) The original motivation behind game theory was to study the effect that multi- ple agents have on each other (Von Neumann and Morgenstern, 1953), known as interdependence or mutual dependence. Essentially, the challenge addresses the ques- tion: why is a group different from the collection of individuals who comprise the group? That the problem remains unsolved almost 70 years later is a remarkable com- ment on the state of the social sciences today, including game theory and economics. But solving this challenge is essential for the science and engineering of multiagent, multirobot and hybrid environments (that is, humans, machines and robots working together).

For any given forecasting problem, contributors The Aggregative Contingent Estimation System (ACES; receive information about the crowd's beliefs immediately see http://www.forecastingace.com) is a project funded by after providing their own forecast.

One of the original applications of crowdsourcing the construction of knowledge is Wikipedia, which relies entirely on people to contribute, extend, and modify the representation of knowledge. This paper presents a case for combining AI and wisdom of the crowds for the social construction of knowledge. Our social-computational approach to collective intelligence combines the strengths of human cognitive diversity in producing content and the capabilities of an AI, through methods such as topic modeling, to link and synthesize across these human contributions. In addition to drawing from established domains such as Wikipedia for inspiration and guidance, we present the design of a system that incorporates AI into wisdom of the crowds to develop a knowledge base on sustainability. In this setting the AI plays the role of scholar, as might many of the other participants, drawing connections and synthesizing across contributions. We close with a general discussion, speculating on educational implications and other roles that an AI can play within an otherwise collective human intelligence.

This paper presents work using crowdsourcing to assess explanations for supervised text classification. In this paper, an explanation is defined to be a set of words from the input text that a classifier or human believes to be most useful for making a classification decision. We compared two types of explanations for classification decisions: human-generated and computer-generated. The comparison is based on whether the type of the explanation was identifiable and on which type of explanation was preferred. Crowdsourcing was used to collect two types of data for these experiments. First, human-generated explanations were collected by having users select an appropriate category for a piece of text and highlight words that best support this category. Second, users were asked to compare human- and computer-generated explanations and indicate which they preferred and why. The crowdsourced data used for this paper was collected primarily via Amazon’s Mechanical Turk, using several quality control methods. We found that in one test corpus, the two explanation types were virtually indistinguishable, and that participants did not have a significant preference for one type over another. For another corpus, the explanations were slightly more distinguishable, and participants preferred the computer-generated explanations at a small, but statistically significant, level. We conclude that computer-generated explanations for text classification can be comparable in quality to human-generated explanations.

A principal seeks production of a good within a limited time-frame with a hard deadline, after which any good procured has no value. There is inherent uncertainty in the production process, which in light of the deadline may warrant simultaneous production of multiple goods by multiple producers despite there being no marginal value for extra goods beyond the maximum quality good produced. This motivates a crowdsourcing model of procurement. We address efficient execution of such procurement from a social planner's perspective, taking account of and optimally balancing the value to the principal with the costs to producers (modeled as effort expenditure) while, crucially, contending with self-interest on the part of all players. A solution to this problem involves both an algorithmic aspect that determines an optimal effort level for each producer given the principal's value, and also an incentive mechanism that achieves equilibrium implementation of the socially optimal policy despite the principal privately observing his value, producers privately observing their skill levels and effort expenditure, and all acting only to maximize their own individual welfare. In contrast to popular "winner take all" contests, the efficient mechanism we propose involves a payment to every producer that expends non-zero effort in the efficient policy.