The INI has a new website!

This is a legacy webpage. Please visit the new site to ensure you are seeing up to date information.

Skip to content



Connecting logic and learning

Amir, E (Illinois)
Monday 15 May 2006, 11:00-12:00

Seminar Room 1, Newton Institute


Many complex domains offer limited information about their exact state and the way actions affect them. For example, a robot exploring a building does not know how pressing a button affects the world, and also may not see the effect of pressing the button immediately. There, we need to learn action models to act effectively, at the same time that we track the (partially observed) state of the domain.

In this presentation I will describe polynomial-time algorithms for learning logical models of actions' effects and preconditions in deterministic partially observable domains. These algorithms represent the set of possible action models compactly, and update it after every action execution and partial observation. This approach is the first tractable learning algorithm for partially observable dynamic domains. I will mention recent extensions of this work to relational domains, and will also discuss potential applications of this work to agents playing adventure games and to formal verification.


[ppt ]


MP3MP3 Real AudioReal Audio

Back to top ∧