Connectionists: CFP: Reinforcement Learning and Search in Very Large Spaces, Workshop at ICML 2010

[Csaba Szepesvari]

(Apologies for cross-postings)

CFP: Reinforcement Learning and Search in Very Large Spaces
Workshop at ICML 2010

June 25th, 2010,  Haifa, Israel

http://institute.unileoben.ac.at/infotech/research/workshops/icml2010-RLsearch/


SCOPE:

This workshop is about reinforcement learning in large state/action
spaces, learning to optimize search, and the relation of these two.

Content-based information retrieval with relevance feedback is a
multi-stage process, where at each stage a user selects the item which
is closest to the requested information from a set of presented items,
until the requested information is found. The task of the search engine
is to present items such that the search terminates in few iterations.
More generally, interactive search concerns multi-stage processes where
a search engine presents some information and as response gets some
feedback, which may be partial and noisy. Since the reward for finding
the requested information is delayed, learning a good search engine from
data can be modeled as a reinforcement problem, but the special
structure of the problem needs to be exploited.

Since for realistic search applications the state space is enormous,
this learning problem is a difficult one. Although the literature of
reinforcement learning offers many powerful algorithms that have been
successful in various difficult applications, we find that there is
still relatively little understanding about when reinforcement learning
might be successful in a realistic application, or what might make
reinforcement learning successful in such an application. Furthermore,
little work has been done on applying reinforcement learning to optimize
interactive search.

Thus this workshop addresses in particular but not exclusively the
following two questions:

* Identify cases when realistically large problems with delayed feedback
can be solved successfully, possibly but not necessarily by
reinforcement learning algorithms. Such algorithm may need to exploit
the special structure of the learning problem. As an example we see
content-based information retrieval.
* Application of learning techniques to develop powerful interactive
search algorithms: optimizing a single search or learning across
searches, with or without probabilistic assumptions.

A partial list of topics relevant to the workshop contains:

* reinforcement learning in large state/action spaces
* automatic state/action aggregation and hierarchical reinforcement learning
* special cases or assumptions which facilitate fast reinforcement learning
* reinforcement learning, relevance feedback, and information retrieval
* search strategies based on relevance feedback
* learning efficient search strategies from multiple search sessions
* applications.


SUBMISSIONS:

We are seeking quality contributions describing recent or ongoing work
in the scope of the workshop. Both theoretical and applied work is
solicited. Submissions on applying learning techniques in a principled
manner - either by providing theoretical guarantees or conclusive
empirical studies - are especially encouraged. We additionally welcome
position papers, in particular papers presenting an important and
promising problem field for discussion, and demonstrations.

Submissions should be either 4-page research papers or 2-page position
papers. Papers must be in English and formatted according to the ICML
2010 stylefiles.

Submission should be sent in PDF to icml2010learninginsearch at gmail.com.

The submissions will be reviewed by two reviewers on the basis of
relevance, significance, technical quality, and clarity, with the goal
of assembling a diverse and stimulating workshop agenda.

At least one of the authors of every accepted contribution is expected
to present the contribution.

As this workshop has no formal proceedings, it is fine for the
submissions to be under consideration elsewhere, as long as they will
not be published at any venue before this workshop takes place.

People interested in submitting or participating in the workshop are
welcome to contact any of the organizers with questions.


IMPORTANT DATES:

* Submission deadline: 8 May 2010
* Notification of acceptance: 23 May 2010
* Workshop date: 25 June 2010

Organizers:

Peter Auer (http://personal.unileoben.ac.at/auer/) - University of Leoben
Samuel Kaski (http://www.cis.hut.fi/sami/ - Aalto University, Helsinki
Csaba Szepesvari (http://www.cs.ualberta.ca/~szepesva/) - University of
Alberta