CSCE 475/875

Seminar Assignment

November 7, 2007

Introduction

The objective of this assignment is to let every group (1) learn to present a paper well and (2) learn to participate in a seminar well. So it is more than a presentation. It is a seminar where you are required to ask good questions and answer questions well.

Setup

E-mail me to let me know the paper and the date that you want to present. Every group must present a different paper from the others. So, the sooner you let me know, the more likely you will get to present the paper that you want to present.

Grading

(1) 40% Summary of Paper

(2) 20% Organization (Time management, flow of presentation, poise, etc.)

(3) 20% Conclusions (Comparisons, insights, etc.)

(4) 20% Q&A and Participation

Dates (with one seminar per date):

December 3, 5, 7, 10, 12, and 14

Papers

You are required to choose one of the following papers. I have the electronic copies of the following papers. If you want one, let me know.

Multiagent Systems and Models

Helleboogh, A., G. Vizzari, A. Uhrmacher, and F. Michel (2007). Modeling Dynamic Environments in Multi-Agent Simulation, Journal of Autonomous Agents and Multiagent Systems, 14:87-116. (hellebooghetal2007)

Horling, B. and V. Lesser (2005). A Survey of Multi-Agent Organizational Paradigms, Knowledge Engineering Review, (horlinglesser2005.pdf)

Huhns, M. N. and M. P. Singh (1999). A Multiagent Treatment of Agenthood, Applied Artificial Intelligence, 13(1-2):3-10. (hughsingh1999.pdf)

Padgham, L. and P. Lambrix (2005). Formalisations of Capabilities for BDI-Agents, Journal of Autonomous Agents and Multiagent Systems, 10:249-271. (padghamlambrix2005)

Pynadath, D. and M. Tambe (2002). The Communicative Multiagent Team Decision Problem: Analyzing Teamwork Theories and Models, Journal of Artificial Intelligence Research, 1(6):389-423. (pynadathtambe2002.pdf)

Valckenaers, P., J. Sauter, C. Sierra, and J. A. Rodriguez-Aguilar (2007). Applications and Environments for Multi-Agent Systems, Journal of Autonomous Agents and Multiagent Systems, 14:61-85. (valckenaersetal2007)

Negotiations and Cooperation

Crawford, E. and M. Veloso (2007). An Experts Approach to Strategy Selection in Multiagent Meeting Scheduling, Journal of Autonomous Agents and Multiagent Systems, 15:5-28. (crawfordveloso2007)

Dunne, P. E., M. Wooldridge, and M. Laurence (2005). The Complexity of Contract Negotiation, Artificial Intelligence, 164(1-2):23-46. (dunneetal2005.pdf)

Dolgov, D. A. and E. H. Durfee (2006) Resource Allocation Among Agents with MDP-Induced Preferences, Journal of Artificial Intelligence Research, 27:505-549. (dolgovdurfee2006.pdf)

Faratin, P., C. Sierra, and N. R. Jennings (1998). Negotiation Decision Functions for Autonomous Agents, Int. Journal of Robotics and Autonomous Systems, 24(3-4):159-182. (faratinetal1998.pdf)

Faratin, P., C. Sierra, and N. R. Jennings (2002). Using Similarity Criteria to Make Issue Trade-Offs in Automated Negotiations, Artificial Intelligence, 142:205-237. (faratinetal2002.pdf)

Grosz, B. and S. Kraus (1996). Collaborative plans for complex group action, Artificial Intelligence, 86(2):269-357. (groszkraus1996.pdf)

Grosz, B. J. and S. Kraus (1998). The evolution of SharedPlans, in Rao, A. and M. Wooldridge (eds.) Foundations and Theories of Rational Agency, Kluwer Academic Publishing. (groszkraus1998.pdf)

Grosz, B. J., S. Kraus, D. G. Sullivan, and S. Das (2002). The Influence of Social Norms and Social Consciousness on Intention Reconciliation, Artificial Intelligence, 142:147-177. (groszetal2002.pdf)

Huynh, T. D., N. R. Jennings, and N. R. Shadbolt (2006). An Integrated Trust and Reputation Model for Open Multi-Agent Systems, Journal of Autonomous Agents and Multiagent Systems, 13:119-154. (huynhetal2006.pdf)

Li, C., J. A. Giampapa, and K. Sycara (2006). Bilateral Negotiation Decisions with Uncertain Dynamic Outside Options, IEEE Transactions on Systems, Man, and Cybernetics, Part C: Special Issue on Game-Theoretic Analysis and Stochastic Simulation of Negotiation Agents, 36(1). (lietal2006.pdf)

Nair, R. and M. Tambe (2005). Hybrid BDI-POMDP Framework for Multiagent Teaming, Journal of Artificial Intelligence Research, 23(4):367-420. (nairtambe2005.pdf)

Parsons, S., C. Sierra and N. R. Jennings (1998). Agents that Reason and Negotiate by Arguing, Journal of Logic and Computation, 8(3):261-292. (parsonsetal1998.pdf)

Raja, A. and V. Lesser (2007). A Framework for Meta-Level Control in Multi-Agent Systems, to appear in Journal of Autonomous Agents and Multiagent Systems. (rajalesser2007.pdf)

Ros, R. and C. Sierra (2006). A Negotiation Meta Strategy Combining Trade-Off and Concession Moves, Journal of Autonomous Agents and Multiagent Systems, 12:163-181. (rossierra2006.pdf)

Sandip, S. (2002). Believing Others: Pros and Cons, Artificial Intelligence, 142:179-203 (sandip2002.pdf)

Soh, L.-K. and C. Tsatsoulis (2005). A Real-Time Negotiation Model and A Multi-Agent Sensor Network Implementation, Journal of Autonomous Agents and Multiagent Systems, 11:215-271. (sohtsatsoulis2005.pdf)

Stone, P., M. L. Littman, S. Singh, and M. Kearns (2001). ATTac-2000: An Adaptive Autonomous Bidding Agent, Journal of Artificial Intelligence Research, 15:189-206.

van der Hoek, W. and M. Wooldridge (2005). On the Logic of Cooperation and Propositional Control, Artificial Intelligence, 164(1-2):81-119. (vanderhoekwooldridge2005.pdf)

Zhang, X., V. Lesser, and R. Podorozhny (2005). Multi-Dimensional, MultiStep Negotiation for Task Allocation in a Cooperative System, Journal of Autonomous Agents and Multiagent Systems, 10:5-40. (zhangetal2005.pdf)

Learning

Banerjee, B. and J. Peng (2007). Generalized Multiagent Learning with Performance Bound, to appear in Journal of Autonomous Agents and Multiagent System. (banerjeepeng2007)

Banerjee, B., S. Sen, and S. Saha (2004). On-Policy Concurrent Reinforcement Learning, Journal of Experimental and Theoretical Artificial Intelligence, 16(4):245-260. (banerjeeetal2004.pdf)

Bowling, M. and M. Veloso (2002). Multiagent Learning Using a Variable Learning Rate, Artificial Intelligence, 136:215-250. (bowlingveloso2002.pdf)

Buffet, O., A. Dutech, and F. Charpillet (2007). Shaping Multi-Agent Systems with Gradient Reinforcement Learning, to appear in Journal of Autonomous Agents and Multiagent Systems. (buffetetal2007.pdf)

Bulka, B., M. Gaston, and M. desJardins (2007). Local Strategy Learning in Networked Multi-Agent Team Formation, Journal of Autonomous Agents and Multiagent Systems, 15:29-45. (bulkaetal2007.pdf)

Enembreck, F. and J.-P. Barthés (2005). ELA—A New Approach for Learning Agents, Journal of Autonomous Agents and Multiagent Systems, 10:215-248. (enembreckbarthes2005.pdf)

Ghavamzadeh, M., S. Mahadevan, and R. Makar (2006). Hierarchical Multi-Agent Reinforcement Learning, Journal of Autonomous Agents and Multiagent Systems, 13:197-229. (ghavamzadehetal2006.pdf)

Panait, L. and S. Luke (2005). Cooperative Multi-Agent Learning: The State of the Art, Journal of Autonomous Agents and Multiagent Systems, 11:387-434. (panaitluke2005.pdf)

Plaza, E. and S. Ontañón (2006). Learning Collaboration Strategies for Committees of Learning Agents, Journal of Autonomous Agents and Multiagent Systems, 13:429-461. (plazaontanon2006.pdf)

Stone, P., R. S. Sutton, and G. Kuhlmann (2005). Reinforcement Learning for RoboCup-Soccer Keepaway, Adaptive Behavior, 13(3):165-188. (stoneetal2005.pdf)

Vidal, J. M. and E. H. Durfee (2003). Predicting the Expected Behavior of Agents that Learn about Agents: The CLRI Framework, Autonomous Agents and Multi-Agent Systems, 6(1):77-107. (vidaldurfee2003.pdf)

Real-Time

Stone, P. and M. Veloso (1999). Task Decomposition, Dynamic Role Assignment, and Low-Bandwidth Communication for Real-Time Strategic Teamwork, Artificial Intelligence, 100(2):241-273. (stoneveloso1999.ps)

Bazzan, A. L. C. (2005). A Distributed Approach for Coordination of Traffic Signal Agents, Journal of Autonomous Agents and Multiagent Systems, 10:131-164. (bazzan2005.pdf)

Monitoring

Kaminka, G. A., D. V. Pynadath, and M. Tambe (2002). Monitoring Teams by Overhearing: A Multi-Agent Plan-Recognition Approach, Journal of Artificial Intelligence Research, 17:83-135. (kaminkaetal2002.pdf)

Nair, R., M. Tambe, S. Marsella, and R. Raines (2004). Automated Assistants for Analyzing Team Behaviors, Journal of Autonomous Agents and Multiagent Systems, 8(1):69-111. (nairetal2004.pdf)

Wilkins, D. E., T. J. Lee, and P. Berry (2003). Interactive Execution Monitoring of Agent Teams, Journal of Artificial Intelligence Research, 18:217-261. (wilkinsetal2003.pdf)

Requirements

Each group is required to give a presentation of close to but no more than 35 minutes (the talk itself). All members of the group must present roughly for the same amount of time. All members of a team receive the same score. (That means, you are required to work together to get your presentation well-oiled. Critique each other when you practice.)

During the 15-minute seminar (Q&A), all members are required to answer questions. If one of you answers no questions, the group will be penalized. I will also ask some questions.

Every group is required to ask at least two questions in each presentation (except for their own presentation).

Every group is required to give me an electronic copy of their presentation at least 3 hours before the class starts on the day of their seminar. So I can make copies for all students.