Human-agent interaction for learning with instruction can would involve pointing the tank in at the enemy tank be viewed on a continuum of instructor/agent control. The environment is partially observable to the instructor or imitation. The other extreme of the continuum is and the task is unknown to the agent, necessitating mixed occupied by systems where instructor interaction is limited initiative, bidirectional information transfer. Our agents are instantiated in Soar (Laird, 2008), a To be able to maintain the state of interactions with the symbolic, cognitive architecture based on the problemspace instructor while acting in the environment, and to be able to hypothesis. A Soar agent's current state is derived learn from these instructions in the context they were from its perceptions, its beliefs about the world and provided in, the agent needs a model of task-oriented knowledge in its long-term memories and is held in its interaction.

Coordination in mixed agent-human environments is an important, yet not a simple, problem. Little attention has been given to the issues raised in teams that consist of both computerized agents and people. In such situations different considerations are in order, as people tend to make mistakes and they are affected by cognitive, social and cultural factors. In this paper we present a novel agent designed to proficiently coordinate with a human counterpart. The agent uses a neural network model that is based on a pre-existing knowledge base which allows it to achieve an efficient modeling of a human's decisions and predict their behavior. A novel communication mechanism which takes into account the expected effect of communication on the other member will allow communication costs to be minimized. In extensive simulations involving more than 200 people we investigated our approach and showed that our agent achieves better coordination when involved, compared to settings in which only humans or another state-of-the-art agent are involved.

Recent works on multi-agent sequential decision making using decentralized partially observable Markov decision processes have been concerned with interaction-oriented resolution techniques and provide promising results. These techniques take advantage of local interactions and coordination. In this paper, we propose an approach based on an interaction-oriented resolution of decentralized decision makers. To this end, distributed value functions (DVF) have been used by decoupling the multi-agent problem into a set of individual agent problems. However existing DVF techniques assume permanent and free communication between the agents. In this paper, we extend the DVF methodology to address full local observability, limited share of information and communication breaks. We apply our new DVF in a real-world application consisting of multi-robot exploration where each robot computes locally a strategy that minimizes the interactions between the robots and maximizes the space coverage of the team even under communication constraints. Our technique has been implemented and evaluated in simulation and in real-world scenarios during a robotic challenge for the exploration and mapping of an unknown environment. Experimental results from real-world scenarios and from the challenge are given where our system was vice-champion.

We join the goals of two giant and related fields of research in group decision-making that have historically had little contact: fair division, and efficient mechanism design with monetary payments. To do this we adopt the standard mechanism design paradigm where utility is assumed to be quasilinear and thus transferable across agents. We generalize the traditional binary criteria of envy-freeness, proportionality, and efficiency (welfare) to measures of degree that range between 0 and 1. We demonstrate that in the canonical fair division settings under any allocatively-efficient mechanism the worst-case welfare rate is 0 and disproportionality rate is 1; in other words, the worst-case results are as bad as possible. This strongly motivates an average-case analysis. We then set as the goal identification of a mechanism that achieves high welfare, low envy, and low disproportionality in expectation across a spectrum of fair division settings. We establish that the VCG mechanism is not a satisfactory candidate, but the redistribution mechanism of [Bailey, 1997; Cavallo, 2006] is.

This paper addresses the problem of automated advice provision in settings that involve repeated interactions between people and computer agents. This problem arises in many real world applications such as route selection systems and office assistants. To succeed in such settings agents must reason about how their actions in the present influence people's future actions. This work models such settings as a family of repeated bilateral games of incomplete information called ``choice selection processes'', in which players may share certain goals, but are essentially self-interested. The paper describes several possible models of human behavior that were inspired by behavioral economic theories of people's play in repeated interactions. These models were incorporated into several agent designs to repeatedly generate offers to people playing the game. These agents were evaluated in extensive empirical investigations including hundreds of subjects that interacted with computers in different choice selections processes. The results revealed that an agent that combined a hyperbolic discounting model of human behavior with a social utility function was able to outperform alternative agent designs, including an agent that approximated the optimal strategy using continuous MDPs and an agent using epsilon-greedy strategies to describe people's behavior. We show that this approach was able to generalize to new people as well as choice selection processes that were not used for training. Our results demonstrate that combining computational approaches with behavioral economics models of people in repeated interactions facilitates the design of advice provision strategies for a large class of real-world settings.

Despite many years of research and progress in the field tecture, the testing environment in which the implementation of artificial intelligence, there is still no universally accepted will be embedded, and then describes the work completed so definition of the word intelligence. Finally we will address the body of work still to be completed identified a multitude of tasks, skills, and behaviours that and plans for future research. Much A.I research is focused Although the initial thrust multiplicity, heterogeneity, and adaptability. of A.I in the 1950s was towards this kind of integrated system, Multiplicity. One of the few points of consensus within in recent times the problem of integration has become cognitive architecture research is that architectures must be conspicuous by its absence in the field, but is essential to improve composed of modular, independent components. This is a our design of complete intelligent systems, and consequently consequence of the multifaceted nature of information processing, our understanding of our own brains.

This paper presents the design and learning architecture for an omnidirectional walk used by a humanoid robot soccer agent acting in the RoboCup 3D simulation environment. The walk, which was originally designed for and tested on an actual Nao robot before being employed in the 2011 RoboCup 3D simulation competition, was the crucial component in the UT Austin Villa team winning the competition in 2011. To the best of our knowledge, this is the first time that robot behavior has been conceived and constructed on a real robot for the end purpose of being used in simulation.  The walk is based on a double linear inverted pendulum model, and multiple sets of its parameters are optimized via a novel framework. The framework optimizes parameters for different tasks in conjunction with one another, a little-understood problem with substantial practical significance.  Detailed experiments show that the UT Austin Villa agent significantly outperforms all the other agents in the competition with the optimized walk being the key to its success.

In order for robots to intelligently perform tasks with humans, they must be able to access a broad set of background knowledge about the environments in which they operate. Unlike other approaches, which tend to manually define the knowledge of the robot, our approach enables robots to actively query the World Wide Web (WWW) to learn background knowledge about the physical environment. We show that our approach is able to search the Web to infer the probability that an object, such as a "coffee,'' can be found in a location, such as a "kitchen.'' Our approach, called ObjectEval, is able to dynamically instantiate a utility function using this probability, enabling robots to find arbitrary objects in indoor environments. Our experimental results show that the interactive version of ObjectEval visits 28% fewer locations than the version trained offline and 71% fewer locations than a baseline approach which uses no background knowledge.

Virtual worlds present a challenge for intelligent mobile agents. They are required to generate maps of very large scale, dynamic and unstructured environments in a short amount of time. We investigate how to represent maps of ever growing virtual environments, how the agent can build, update and use these maps to navigate between points in the environment. We look at trails, the movement of other people and agents in the environment as a new information source. We can use trails to improve the generation of probabilistic roadmaps in these environments and enable the agent to segment space intelligently. Our future plans are to extend this to look at dynamic environments, where the agent will have to recognise change and update the map and how this will affect the map representation.

Designing revenue-optimal auctions for various settings is perhaps the most important, yet sometimes most elusive, problem in mechanism design. Spiteful bidders have been intensely studied recently, especially because spite occurs in many applications in multiagent system and electronic commerce. We derive the optimal auction for such bidders (as well as bidders that are altruistic). It is a generalization of Myerson’s (1981) auction. It chooses an allocation that maximizes agents’ virtual valuations, but for a generalized definition of virtual valuation. The payment rule is less intuitive. For one, it takes each bidder’s own report into consideration when determining his payment. Moreover, bidders pay even if the seller keeps the item; a similar phenomenon has been shown in other settings with neg- ative externalities (Jehiel, Moldovanu, and Stacchetti 1996; Deng and Pekec 2011). On the other hand, a novel aspect of our auction is that it sometimes subsidizes losers when the item is sold to some other bidder. We also derive a revenue equivalence theorem for this setting. Using it, we generate a short proof of (a slight generalization of) the previously known result that, in two-bidder settings with independently uniformly drawn valuations, second-price auctions yield greater expected revenue than first-price auctions. Finally, we present a template for comparing the expected revenues of any two auction mechanisms that have the same allocation rule (for the valuations distributions at hand).