ICML-2001
Schedule for Talks


Friday, June 29

9:15 - 10:30 AM Session 1

Invited Talk (Plenary)

10:30 - 11:00 AM Break

11:00 - 12:15 PM Session 2

Applications of Reinforcement Learning/Robot Learning (Track 1) Ensemble Methods (Track 2) NLP/Information Extraction (Track 3)

12:15 - 1:45 PM Lunch Break

1:45 - 3:25 PM Session 3

MultiAgent Learning (Track 1) Unsupervised Learning (Track 2)

3:25 - 4:00 PM Break

4:00 - 5:15 PM Session 4

Reinforcement Learning: The Explore/Exploit Tradeoff (Track 1) Hypertext Categorization and Information Retrieval (Track 2) Multiple Instance Learning/Hypothesis Selection (Track 3)

7:00 - 9:30 PM Poster Session/Reception

Saturday, June 30

9:00 - 10:05 AM Session 5

Invited Talk (Plenary)

10:05- 10:30 AM Session 6

Unsupervised Learning (Track 1) Function Selection (Track 2) Bayesian Learning (Track 3)

10:30 - 11:00 AM Break

11:00 - 12:15 PM Session 7

Bayesian Learning (Track 1) Supervised Learning/Applications (Track 2) Active Sampling/Kernel Density Estimation (Track 3)

12:15 - 1:45 PM Lunch Break

1:45 - 3:25 PM Session 8

Structure in Reinforcement Learning (Track 1) Supervised Learning/Applications (Track 2)

3:25 - 4:00 PM Break

4:00 - 5:15 PM Session 9

SVM and Regression (Track 1) Learning in Relational Representations/ Reinforcement Learning (Track 2) Feature Selection (Track 3)

7:00 - 9:30 PM Poster Session/Reception

Sunday, July 1

9:00 - 10:05 AM Session 10

Invited Talk (Plenary)

10:05 - 10:30 AM Session 11

Reinforcement Learning (Track 1) Unsupervised Learning (Track 2)

10:30 - 11:00 AM Break

11:00 - 12:15 PM Session 12:

Reinforcement Learning: Searching in Policy Space (Track 1) Decision Trees (Track 2) IR and SVM (Track 3)

12:15 - 1:45 PM Lunch Break

1:45 - 3:25 PM Session 13

Sequence Learning (Track 1) Boosting (Track 2)

3:25 - 4:00 PM Break

4:00 - 4:50 PM Session 14

Temporal Difference Learning/Stochastic algorithms (Track 1) Local Learning (Track 2) COLT (Track 3)

5:00 - 6:00 PM Business Meeting

7:00 - 9:30 PM Poster Session/Reception