Schedule and Slides
- Jan 9 - Intro
to CI, Dimensions
of complexity, robot
systems.
- Jan 11 - Simple
Game.
- Jan 16 - Decision-theoretic
planning. See the value
iteration applet.
- Jan 18 - decision-theoretic planning (cont).
- Jan 23 - Reinforcement
Learning. See the Q-learning
applet
- Jan 25 - Reinforcement learning (cont). Online versus offline learning.
Function approximation.
- Jan 30 - RL (cont). Evaluating RL algorithms. Review of function
approximation. Neural network overview. Model-based approaches.
- Feb 1 - RL (cont). Features for our game. Genetic Algorithms for RL.
Extending our game.
- Feb 6 - adversaries and other agents (multi-agent systems) game
theory.
- Feb 8 - multi-agent systems (cont)
- Feb 13 - review of Bayesian networks, partial observability Probability
and time, Localization
demo, Sebastian Thrun's Monte Carlo Localization
videos.
- Feb 15 - Probability and time (cont)
- Feb 27 - POMDP overview and Learning
probabilities, Learning
probabilities demo.
- Mar 1 - Guest lecturer Pantelis
Elinas
- Mar 6 - learning probabilities (continued)
- Mar 8 - Midterm
- Mar 13 - knowledge
representation, semantic
networks.
- Mar 15 - ontologies
- Mar 20 - ontologies (cont). HomeOwner.owl,
two implementations of the residential building ontology MultiDimBuilding.owl and MultiDimBuilding2.owl. These were
created using Protégé.
- Mar 22 - Knowledge-based
systems and knowledge-based
explanation and debugging.
- Mar 27 - KBSs (cont) Meta-Interpreters
- More
Meta-Interpreters.
- Mar 29 - Integrity
Constraints and negation, Assumption-based reasoning.
- Apr 3 - Abduction
and Default
Reasoning
- Apr 5 - Abduction and Probabilistic Reasoning
- Apr 10 - Project Presentations
- Apr 12 - Course Overview
- Apr 25, 8:30am, Final Exam!, DMP 201
David Poole - 2007-03-26