AAMAS Awards 2010
There are a number of awards associated with the AAMAS conference, some of which are known in advance, and some of which are announced at the conference.
ACM SIGART Autonomous Agents Research Award
The ACM SIGART Autonomous Agents Research Award is an annual award for excellence in research in the area of autonomous agents. The award is intended to recognize researchers in autonomous agents whose current work is an important influence on the field. The award is an official ACM award, funded by an endowment created by ACM SIGART from the proceeds of previous Autonomous Agents conferences. Candidates for the award are nominated through an open nomination process. Previous winners of the SIGART Autonomous Research Award were Manuela Veloso (2009), Yoav Shoham (2008), Sarit Kraus (2007). Michael Wooldridge (2006), Milind Tambe (2005), Makoto Yokoo (2004), Nick Jennings (2003), Katia Sycara (2002), and Tuomas Sandholm (2001).
The 2010 ACM SIGART Autonomous Agents Research Award recipients are Prof. Jonathan Gratch and Prof. Stacy Marsella from the University of Southern California Institute for Creative Technologies, who share the award for their significant and sustained contributions to autonomous agents and multiagent systems in the area of virtual agents, in particular in emotion modeling and social simulation.
IFAAMAS Victor Lesser Distinguished Dissertation Award
This award was started for dissertations defended in 2006 and is named for Professor Victor Lesser, a long standing member of the AAMAS community who has graduated a large number of outstanding PhD students in the area. To be eligible for the 2008 award, a dissertation had to have been written as part of a PhD defended during the year 2008, and had to be nominated by the supervisor with three supporting references. Selection is based on originality, depth, impact and written quality, supported by quality publications. Previous winners of this award were Ariel Procaccia (2008), Radu Jurca (2007), and Vincent Conitzer (2006).
The 2009 IFAAMAS Victor Lesser Distinguished Dissertation Award recipient is Dr. Andrew Gilpin of Carnegie Mellon University (advised by Prof. Tuomas Sandholdm) for his dissertation titled "Algorithms for Abstracting and Solving Imperfect Information Games".
Due to the extremely close competition this year, two additional candidates were selected for runner-up prizes. In particular, these are Dr. Kurt Dresner of the University of Texas at Austin (advised by Prof. Peter Stone) for his thesis titled "Autonomous Intersection Management", and Dr. Noa Agmon of Bar Ilan University (advised by Prof. Gal Kaminka and Prof. Sarit Kraus) for her dissertation titled "Multi-Robot Patrolling and Other Multi-Robot Cooperative Tasks: An Algorithmic Approach".IFAAMAS Influential Paper Award
The International Foundation for Autonomous Agents and Multi-Agent Systems set up an influential paper award in 2006 to recognize publications that have made seminal contributions to the field. Such papers represent the best and most influential work in the area of autonomous agents and multi-agent systems. These papers might, therefore, have proved a key result, led to the development of a new sub-field, demonstrated a significant new application or system, or simply presented a new way of thinking about a topic that has proved influential. The award is open to any paper that was published at least 10 years before the award is made. The paper can have been published in any journal, conference, or workshop. The award is sponsored by the Agent Theories, Architectures and Languages foundation.
Previous awards are as follows:
2009
M. N. Huhns. (Ed.) (1987) Distributed Artificial Intelligence. London, Pitman.
A. Bond and L. Gasser. (Eds.) (1988) Readings in Distributed Artificial Intelligence. San Mateo, CA, Morgan Kaufmann.
L. Gasser and M. N. Huhns. (Eds.) (1989) Distributed Artificial Intelligence (Volume II). Pitman and Morgan Kaufmann.
2008
M. E. Bratman, D. J. Israel and M. E. Pollack (1988) Plans and resource-bounded practical reasoning. Computational Intelligence, 4, pages 349-355.
E. H. Durfee and V. Lesser (1991) Partial global planning: A coordination framework for distributed hypothesis formation. In: IEEE Transactions on Systems, Man, and Cybernetics, 21, pages 1167-1183.
2007
J. S. Rosenschein and M. R. Genesereth (1985) Deals Among Rational Agents. In: Proceedings of the 9th International Joint Conference on Artificial Intelligence, Los Angeles , California , August 1985, pages 91-99.
A. Rao and M. Georgeff (1991) Modelling rational agents within a BDI-architecture. In: Proceedings of the 2nd International Conference on Principles of Knowledge Representation and Reasoning, Cambridge, Massachussets, pages 473-484.
B. J. Grosz and S. Kraus (1996) Collaborative Plans for Complex Group Actions. Artificial Intelligence, 86, pages 269-358.
2006
P. R. Cohen and H. Levesque (1990) Intention is choice with commitment. Artificial Intelligence , 42(2-3), pages 213-261.
R. Davis and R. Smith (1983) Negotiation as a Metaphor for Distributed Problem Solving. Artificial Intelligence, 20(1), pages 63-109.
The winners of the 2010 IFAAMAS Influential Paper Award are:
Makoto Yokoo, Edmund H. Durfee, Toru Ishida, and Kazuhiro Kuwabara (1998) The Distributed Constraint Satisfaction Problem: Formalization and Algorithms. IEEE Transactions on Knowledge and Data Engineering 10:673-685
Makoto Yokoo and Katsutoshi Hirayama (1996) Distributed Breakout Algorithm for Solving Distributed Constraint Satisfaction Problems Second. International Conference on Multiagent Systems (ICMAS-96), pp.401-408
Pragnesh Jay Modi Best Student Paper Award
This award is made annually at the AAMAS conference to the paper that is judged to be the best paper at the conference whose main author is registered as a student at the time of paper submission. Typically the student is registered for a PhD, although undergraduate and masters student papers may also be considered. The winning paper may have multiple authors, not all required to be students, but to be eligible, the main author of the paper must be a student. The award is sponsored the Autonomous Agents and Multi-Agent Systems journal.
The award is named after Pragnesh Jay Modi (1975—2007), an active and influential member of the AAMAS research community who died tragically young in April 2007. Jay obtained his PhD from the University of Southern California in 2003, and at the time of his death was a junior faculty member at Drexel University, Philadelphia. Jay's PhD thesis has been foundational in the area of distributed constraint optimization (DCOP), and among his many accomplishments were an NSF-CAREER award and IEEE Intelligent Systems magazine's award for "AI's 10 to watch".
Nominations for the award are made by Program Committee members, Senior Program Committee members, Area Chairs and Program Chairs. The nominees for the AAMAS 2010 Pragnesh Jay Modi Best Student Paper Award are the following:
259We introduce the novel problem of inter-robot transfer learning for perceptual classification of objects, where multiple heterogeneous robots communicate and transfer learned object models consisting of a fusion of multiple object properties. Unlike traditional transfer learning, there can be severe differences in the data distributions, resulting from differences in sensing, sensory processing, or even representations, that each robot uses to learn. Furthermore, only some properties may overlap between the two robots. We show that in such cases, the abstraction of raw sensory data into an intermediate representation can be used not only to aid learning, but also the transfer of knowledge. Further, we utilize statistical metrics, learned during an interactive process where the robots jointly explore the environment, to determine which underlying properties are shared between the robots. We demonstrate results in a visual classification task where objects are represented via a combination of properties derived from different modalities: color, texture, shape, and size. Using our methods, two heterogeneous robots utilizing different sensors and representations are able to successfully transfers support vector machine (SVM) classifiers among each other, resulting in speedups during learning. Inter-Robot Transfer Learning for Perceptual Classification
653As learning agents move from research labs to the real world, it is increasingly important that human users, including those without programming skills, be able to teach agents desired behaviors. Recently, the TAMER framework was introduced for designing agents that can be interactively shaped by human trainers who give only positive and negative feedback signals. Past work on TAMER showed that shaping can greatly reduce the sample complexity required to learn a good policy, can enable lay users to teach agents the behaviors they desire, and can allow agents to learn within a Markov Decision Process (MDP) in the absence of a coded reward function. However, TAMER does not allow this human training to be combined with autonomous learning based on such a coded reward function. This paper leverages the fast learning exhibited within the TAMER framework to hasten a reinforcement learning (RL) algorithm's climb up the learning curve, effectively demonstrating that human reinforcement and MDP reward can be used in conjunction with one another by an autonomous agent. We tested eight plausible TAMER+RL methods for combining a previously learned human reinforcement function, $\hat{H}$, with MDP reward in a reinforcement learning algorithm. This paper identifies which of these methods are most effective and analyzes their strengths and weaknesses. Results from these TAMER+RL algorithms indicate better final performance and better cumulative performance than either a TAMER agent or an RL agent alone. Combining Manual Feedback with Subsequent MDP Reward Signals for Reinforcement Learning
711Learning, planning, and representing knowledge in large state spaces at multiple levels of temporal abstraction are key, long-standing challenges for building flexible autonomous agents. The options framework provides a formal mechanism for specifying and learning reusable temporally-extended skills. Although past work has demonstrated the benefit of acting according to options in large state spaces, one of the central advantages of temporal abstraction - the ability to plan using a temporally abstract model - remains a challenging problem when the number of environment states is large or infinite. In this work, we develop a knowledge construct, the linear option, which is capable of modeling temporally abstract dynamics in large state spaces. We show that planning with a linear expectation model of an option's dynamics converges to a fixed point with low Temporal Difference (TD) error. Next, building on recent work on linear feature selection, we show conditions under which a linear feature set is sufficient for accurately representing the value function of an option policy. We extend this result to show conditions under which multiple options may be repeatedly composed to create new options with accurate linear models. Finally, we demonstrate linear option learning and planning algorithms in a simulated robot environment.Linear Options
Note that all Pragnesh Jay Modi Best Student Papers Award nominations are also nominated for the iRobot Best Paper Award.
iRobot Best Paper Award
This award is for a selected paper which does not have a student as primary author. Nominations are made by Program Committee members, Senior Program Committee members, Area Chairs and Program Chairs. The award is sponsored by iRobot.
The nominees for the AAMAS 2010 iRobot Best Paper Award are the following:
186Many problems in multiagent decision making can be addressed using tournament solutions, i.e., functions that associate with each completeand asymmetric relation on a set of alternatives a non-empty subset of the alternatives. For any given tournemant solution $S$, there is another tournament solution $\dot{S}$, which returns the union of all inclusion-minimal sets that satisfy S-retentiveness, a natural stability criterion with respect to S. Schwartz's tournament equilibrium set ($TEQ$) is then defined as $TEQ = T\dot{E}Q$. Due to this unwieldy recursive definition, preciously little is known about $TEQ$. Contingent on a well-known conjecture about $TEQ$, we show that $\dot{S}$ inherits a number of important and desirable properties from $S$. We thus obtain an infinite hierarchy of attractive and efficiently computable tournament solutions that "approximate" $TEQ$, which itself is intractable. This hierarchy contains well-known tournament solutions such as the top cycle ($TC$) and the minimal covering set ($MC$). We further pove a weaker version of the conjecture mentioned above, which establishes $\dot{T}C$ as an attractive new tournament solution. Minimal Retentive Sets in Tournaments
283The use of energy storage devices in homes has been advocated as one of the main ways of saving energy and reducing the reliance on fossil fuels in the future Smart Grid. However, if micro-storage devices are all charged at the same time using power from the electricity grid, it means a higher demand and, hence, more generation capacity, more carbon emissions, and, in the worst case, breaking down the system due to over-demand. To alleviate such issues, in this paper, we present a novel agent-based micro-storage management technique that allows all (individually-owned) storage devices in the system to converge to profitable, efficient behaviour. Specifically, we provide a general framework within which to analyse the Nash equilibrium of an electricity grid and devise new agent-based storage learning strategies that adapt to market conditions. Taken altogether, our solution shows that, specifically, in the UK electricity market, it is possible to achieve savings of up to 13\% on average for a consumer on his electricity bill with a storage device of 4 kWh. Moreover, we show that there exists an equilibrium where only 38\% of UK households would own storage devices and where social welfare would be also maximised (with an overall annual savings of nearly GBP 1.5B at that equilibrium). Agent-based Micro-Storage Management for the Smart Grid
697Large heterogeneous teams will often be in situations where sensor datathat is uncertain and conflicting is shared across a peer-to-peer network.Not every team member will have direct access to sensors and team members will be influenced mostly by teammates with whom they communicatedirectly. In this paper, we investigate the dynamics and emergent behaviors of a large team sharing beliefs to reach conclusions about the world.We find empirically that the dynamics of information propagation in suchbelief sharing systems are characterized by information avalanches of belief changes caused by a single additional sensor reading. The distributionof the size of these avalanches dictates the speed and accuracy with whichthe team reaches conclusions. A key property of the system is that it exhibits qualitatively different dynamics and system performance over smallchanges in system parameter ranges. In one particular range, the systemexhibits behavior known as scale-invariant dynamics which we empiricallyfind to correspond to dramatically more accurate conclusions being reachedby team members. Due to the fact that the ranges are very sensitive toconfiguration details, the parameter ranges over which specific system dynamics occur are extremely difficult to predict precisely. In this paper we(a) develop techniques to mathematically characterize the dynamics of theteam belief propagation (b) obtain through simulations the relation betweenthe dynamics and overall system performance, and (c) develop a novel distributed algorithms that the agents in the team use locally to steer the wholeteam to areas of optimized performance. Exploiting Scale Invariant Dynamics for Efficient Information Propagation in Teams
Best Virtual Agents Paper Award
This award is open for all papers submitted to AAMAS 2010 with a clear relevance to virtual agents. It is for the best paper in the area submitted to the conference. The selection committee consists of the Virtual Agents Special Track Chair, and the Program Chairs. This award is for a selected paper which does not have a student as primary author and is submitted to the Virtual Agent track. Nominations are made by Program Committee members, Senior Program Committee members, Area Chairs and Program Chairs.
The nominees for the AAMAS 2010 Best Virtual Agent Paper Award are the following:
739Virtual human research has often modeled nonverbal behaviors based on the findings of psychological research. Inrecent years, however, there have been growing efforts touse automated, data-driven approaches to find patterns ofnonverbal behaviors in video corpora and even thereby discover new factors that have not been previously documented.However, there have been few studies that compare how thebehaviors generated by different approaches are interpretedby people. In this paper, we present an evaluation study tocompare the perception of nonverbal behaviors, more specifically head nods, generated by different approaches. Studieshave shown that head nods serve a variety of communicative functions and that the head is in constant motion duringspeaking turns. To evaluate the different approaches of headnod generation, we asked human subjects to evaluate videosof a virtual agent displaying nods generated by a human,by a machine learning data-driven approach, or by a handcrafted rule-based approach. Results show that there is asignificant effect on the perception of head nods in termsof appropriate nod occurrence, especially between the data-driven approach and the rule-based approach. Evaluating Models of Speaker Head Nods for Virtual Agents
786In this paper, we present a new trajectory planning algorithm for virtual humans. Our approach focuses on implicitcooperation between multiple virtual agents in order to sharethe work of avoiding collisions with each other. Specifically,we extend recent work on multi-robot planning to bettermodel how humans avoid collisions by introducing new parameters that model human traits, such as reaction timeand biomechanical limitations. We validate this new modelbased on data of real humans walking captured by the Locanthrope project. We also show how our model extendsto complex scenarios with multiple agents interacting witheach other and avoiding nearby obstacles. Modeling Collision Avoidance Behavior for Virtual Humans
798Virtual humans are embodied software agents that should not onlybe realistic looking but also have natural and realistic behaviors.Traditional virtual human systems learn these interactionbehaviors by observing how individuals respond in face-to-facesituations (i.e., direct interaction). In contrast, this paperintroduces a novel methodological approach called parasocialconsensus sampling (PCS) which allows multiple individuals tovicariously experience the same situation to gain insight on thetypical (i.e., consensus view) of human responses in socialinteraction. This approach can help tease apart what isidiosyncratic from what is essential and help reveal the strength ofcues that elicit social responses. Our PCS approach has severaladvantages over traditional methods: (1) it integrates data frommultiple independent listeners interacting with the same speaker,(2) it associates probability of how likely feedback will be givenover time, (3) it can be used as a prior to analyze and understandthe face-to-face interaction data, (4) it facilitates much quickerand cheaper data collection. In this paper, we apply our PCSapproach to learn a predictive model of listener backchannelfeedback. Our experiments demonstrate that a virtual humandriven by our PCS approach creates significantly more rapportand is perceived as more believable than the virtual human drivenby face-to-face interaction data. Parasocial Consensus Sampling: Combining Multiple Perspectives to Learn Virtual Human Behavior
CoTeSys Best Robotics Paper Award
This award is open for all papers submitted to AAMAS 2010 with a clear relevance to robotics. It is for the best paper in the area submitted to the conference. The selection committee consists of the Robotics Special Track Chair, and the Program Chairs. The award is sponsored by CoTeSys, the German Cluster of Excellence.
The nominees for the AAMAS 2010 CoTeSys Best Robotics Paper Award are the following:
259We introduce the novel problem of inter-robot transfer learning for perceptual classification of objects, where multiple heterogeneous robots communicate and transfer learned object models consisting of a fusion of multiple object properties. Unlike traditional transfer learning, there can be severe differences in the data distributions, resulting from differences in sensing, sensory processing, or even representations, that each robot uses to learn. Furthermore, only some properties may overlap between the two robots. We show that in such cases, the abstraction of raw sensory data into an intermediate representation can be used not only to aid learning, but also the transfer of knowledge. Further, we utilize statistical metrics, learned during an interactive process where the robots jointly explore the environment, to determine which underlying properties are shared between the robots. We demonstrate results in a visual classification task where objects are represented via a combination of properties derived from different modalities: color, texture, shape, and size. Using our methods, two heterogeneous robots utilizing different sensors and representations are able to successfully transfer support vector machine (SVM) classifiers among each other, resulting in speedups during learning.Inter-Robot Transfer Learning for Perceptual Classification
441We introduce a novel case study in which a group of miniaturized robots screen an environment for undesirable agents, and destroy them. Because miniaturized robots are usually endowed with reactive controllers and minimalist sensing and actuation capabilities, they must collaborate in order to achieve their task efficiently. In this paper, we show how aggregation can mediate both collective perception and action while maintaining the scalability of the algorithm. First, we demonstrate the feasibility of our approach by implementing it on a real group of Alice mobile robots, which are only two centimeters in size. Then, we use a combination of both realistic simulations and macroscopic models in order to find optimal parameters that maximize the number of undesirable cells destroyed while minimizing the impact on the healthy population. Finally, we discuss the limitations of these models, both in terms of accuracy, computational cost, and scalability, and we outline the importance of an appropriate multi-level modeling methodology to ensure the relevance and the faithfulness of such models.Aggregation-mediated Collective Perception and Action in a Group of Miniature Robots
566We consider a heterogeneous swarm consisting of aerial and wheeled robots. We present a system that enables spatially targeted communication. Our system enables aerial robots to establish dedicated communication links with individual wheeled robots or with selected groups of wheeled robots based on their position in the environment. The system does not rely on any form of global information. We show how a spatially targeted one-to-one communication link can be established using a simple LED and camera based communication modality. We provide a probabilistic model of our approach to derive an upper bound on the average time required for establishing communication. In simulation, we show that our approach scales well. Furthermore, we show how our approach can be extended to establish a spatially targeted one-to-many communication link between an aerial robot and a specific number of co-located wheeled robots. The heterogeneous swarm robotic hardware is currently under development. We therefore demonstrate the proposed approach on an existing multirobot system consisting of only wheeled robots by letting one of the wheeled robots assume the role of an aerial robot.Establishing Spatially Targeted Communication in a Heterogeneous Robot Swarm
Best Industry Track Paper Award
This award is for a selected paper from the Industry track. The award selection will be done in consultation by the advisory board and the industry track co-chairs.
Best Demo Award
A best demo award will be chosen, and will include a cash prize of $1000. The award selection will be done by the exhibits and demos co-chairs in consultation with the Advisory Board.
Best Senior Program Committee Member Award
This award is for a selected member of the Senior Program Committee based on outstanding contribution to the management of the paper selection process, including reviewing, encouraging discussion, obtaining extra reviews if needed, and dealing with any issues arising in the course of paper selection.
The nominees for the AAMAS 2010 Best Senior Program Committee member are Vincent Contizer, Mehdi Dastani and Pedro Lima.
Best Program Committee Member Award
This award is for a selected member of the Program Committee based on outstanding quality of reviews and discussion of papers.
The nominees for the AAMAS 2010 Best Senior Program Committee member are Amit Chopra, Paul Harrenstein and Alexandra Kirsch.