About
Traditional off-line learning methods are often not appropriate for applications in user modelling and user interfaces since to be useful the system must learn about the user or context during the process of interaction 'on the fly'. This immediately raises the fundamental problem of trading off exploration and exploitation in that as information is learnt the system may be tempted to act in line with this insight rather than further exploring alternatives. Machine learning has developed a number of models that attempt to capture and analyse this trade-off, from the simplest bandit problem to the full Markov decision processes underlying reinforcement learning.
The workshop includes tutorials covering the bandit analysis as well as its relevance to user modelling. Reinforcement learning would also be included with particular emphasis on applications in user interfaces. It is also hoped to launch a challenge in this area. This workshop comes under the Thematic Programme 4: Online User Modelling and Reinforcement Learning and is a core meeting of the PASCAL Network.
Videos
Lectures

Research Problems in applaying RL in Interactive Systems Towards a Taxonomy...
Feb 25, 2007
·
3041 views

Overview of Results Pump Priming Project
Feb 25, 2007
·
2958 views

Clustering from an Optimization viewpoint Exploration and Exploitation using Upp...
Feb 25, 2007
·
4294 views

Models for Trading Exploration and Exploitation using Upper Confidence Bounds
Feb 25, 2007
·
3682 views

Presentation of proposed outline challenge
Feb 25, 2007
·
3740 views

The exploration and exploitation tradeoff: Strategy learning and queries
Feb 25, 2007
·
3702 views

Gradient-Based Estimates of Return Distributions
Feb 25, 2007
·
2583 views

mSpace
Feb 25, 2007
·
3117 views

Multiarmed Bandits and Partial Monitoring Exploration and Exploitation using Upp...
Feb 25, 2007
·
3966 views