....................
UC BERKELEY AI-AGENTS READING GROUP:

Spring Schedule 2002

Coordinated by: Eyal Amir


Table of Contents

Reading Group Admin
.
This Semester's Reading Schedule.
Participants
.
Miscellaneous Resources
.


Reading Group Admin


TIME: Tuesdays, 12:30pm until 2pm.
LOCATION & DIRECTIONS: Soda Hall, 7th floor alcove, or Stuart Russell's office (Campus Map (Soda Hall is at A4-A5))
INFORMATION: eyal@cs.berkeley.edu
ANNOUNCEMENTS: Register to the AI-Agents reading group mailing list by sending an email to majordomo@uclink.berkeley.edu with the body "subscribe ai-agents".

The AI-Agents reading group is interested in a variety of topics including, but not limited to:

+ Architectures that combine perception, learning, knowledge representation and reasoning and action;
+ Adding knowledge to agents by hand or by controlled learning;
+ Combining "behaviors" to produce complex systems;
+ Tractability and real-time approximations for reasoning;
+ Convergence of reactive behavior to a goal or to an "acceptable" solution.
+ Combining different kinds of knowledge in agents (e.g., utilities, probabilistic belief models, hand-crafted knowledge, and control knowledge).
+ Agents in games (actual games and game-theoretic agents), including interactive games (e.g., Doom or Command&Conquer), adventure games and knowledge-using games (e.g., text-based or D&D) and multi-player games (e.g., MUDS), and coordination of collaborating agents.
+ Coping with severe lack of knowledge (e.g., you do not know what actions you can perform in the next room).
+ Learning the behavior of the environment and its reaction to the agent's actions (e.g., how do you know that your action in this room does not influence the state in another room? what if you do not know, and how will you fix it when you find out later?).


Spring 2002 Readings

+ Mon Feb 4 Craig Boutilier, Ray Reiter, Mikhail Soutchanski, and Sebastian Thrun. Decision-theoretic, high-level agent programming in the situation calculus. In Proceedings of the 7th Conference on Artificial Intelligence (AAAI-00), pages 355-362, 2000. AAAI Press.
+ Mon Feb 11 1. Barbara Hayes-Roth, A blackboard architecture for control, Artificial Intelligence journal, vol. 26, 1985.
2. Barbara Hayes-Roth, Intelligent control, Artificial Intelligence journal, vol. 59, 1993.
3. Play the Lima MUD game.
+ Mon Feb 25 1. Same as for Feb 11.
2. Richard S. Sutton, Integrated architecture for learning, planning and reacting based on approximating dynamic programming, 7th Int'l conference on machine learning (ICML'90), pp. 216--224, Morgan Kaufmann, 1990.
3. Andrew W. Moore and Christopher G. Atkenson, Prioritized sweeping: reinforcement learning with less data and less real time
4. Nir Friedman and Ron Parr, Generalized prioritized sweeping.
+ Mon Mar 4 1. Richard S. Sutton, Integrated architecture for learning, planning and reacting based on approximating dynamic programming, 7th Int'l conference on machine learning (ICML'90), pp. 216--224, Morgan Kaufmann, 1990.
2. Andrew W. Moore and Christopher G. Atkenson, Prioritized sweeping: reinforcement learning with less data and less real time
3. Nir Friedman and Ron Parr, Generalized prioritized sweeping.
+ Mon Mar 11 1. Rodney A. Brooks, A robust layered control system for a mobile robot, IEEE journal of robotics and automation, vol 2(1), pp. 14--23 (1986).
2. Rodney A. Brooks, Integrated Systems Based on Behaviors, SIGART Bulletin (2:4), August 1991, pp. 46-50.
3. Rodney A. Brooks, From Earwigs to Humans, Robotics and Autonomous Systems, Vol. 20(2-4), June 1997, pp. 291-304.
+ Mon Mar 18 1. Patti Maes, The Dynamics of Action Selection, IJCAI'1989.
2. Ron Arkin, Behavior-Based Robotics, Chapter 4, MIT Press 1998.
+ Mon Apr 1 Carlos Guestrin, Daphne Koller and Ronald Parr, Multiagent Planning with Factored MDPs, Advances in Neural Information Processing Systems (NIPS-14) 2001.
+ Mon Apr 8 Daphne Koller and Ronald Parr, Computing Factored Value Functions for Policies in Structured MDPs, IJCAI'99, 1999.
+ Mon Apr 15 Stanley J. Rosenschein and Leslie Pack Kaelbling, A Situated View of Representation and Control, Artificial Intelligence, Vol. 73, 1995.


Attending Participants

Eyal Amir
David Andre
Barbara Engelhardt
Andrea Frome
Greg Lawrence
Bhaskara Marthi
Mark Paskin
Tye Rattenbury
Stuart Russell
Kamin Whitehouse


Related People and Projects

Patrick Doyle.

Miscellaneous Resources

John Laird
Alexander Nareyek's EXCALIBUR and DragonBreath.
AI-Robotics-Vision seminar at UC Berkeley.
Other seminars in the Computer Science Division.
Upcoming UC Berkeley CS Seminars.
Broad Area Colloquium at Stanford.
SRI's AI Seminar Series.
UC Berkeley's Electronic Systems Design (ESD) Seminar Series.
Institute for Cognitive and Brain Sciences at UC Berkeley.


Eyal Amir or home-page
Last modified: Wed Aug 28 18:36:55 PDT 2002