Pollack, Jordan
Emergent Resource Exchange and Tolerated Theft Behavior using Multi-Agent Reinforcement Learning
Garbus, Jack, Pollack, Jordan
For decades, the evolution of cooperation has piqued the interest of numerous academic disciplines such as game theory, economics, biology, and computer science. In this work, we demonstrate the emergence of a novel and effective resource exchange protocol formed by dropping and picking up resources in a foraging environment. This form of cooperation is made possible by the introduction of a campfire, which adds an extended period of congregation and downtime for agents to explore otherwise unlikely interactions. We find that the agents learn to avoid getting cheated by their exchange partners, but not always from a third party. We also observe the emergence of behavior analogous to tolerated theft, despite the lack of any punishment, combat, or larceny mechanism in the environment.
Letters to the Editor
Mostow, Jack, Mostow, Janet Tyroler, Pollack, Jordan, Hendler, James A., Slagle, James R., Wick, Michael R., Akman, Varol
Thanks from Jack and Janet Mostow for causing them to meet at AAAI'87 and subsequently marry; a correction to Jordan Pollack's affiliation; a correction to the winter 1988 wording of his report on Workshop on Theoretical Issues in Conceptual Information Processing; an addendum to the Slagle and Wick article in 9, 4: A Method for Evaluating Candidate Expert System Applications, citing Bruno Franck, and comments on Intelligent Computer-Aided Engineering by Kenneth D. Forbus in vol 9, no 3.
High-Level Connectionist Models
Pollack, Jordan
A workshop on high-level connectionist models was held in Las Cruces, New Mexico, on 9-11 April 1988 with support from the Association for the Advancement of Artificial Intelligence and the Office of Naval Research. John Barnden and Jordan Pollack organized and hosted the workshop and will edit a book containing the proceedings and commentary. The book will be published by Ablex as the first volume in a series entitled Advances in Connectionist and Neural Computation Theory.