We consider online learning where the target concept can change over time. Previous work on expert prediction algorithms has bounded the worst-case performance on any subsequence ...
Bayesian learning, widely used in many applied data-modeling problems, is often accomplished with approximation schemes because it requires intractable computation of the posterio...
We apply an adapted version of Particle Swarm Optimization to distributed unsupervised robotic learning in groups of robots with only local information. The performance of the lea...
Distributed W-Learning (DWL) is a reinforcement learningbased algorithm for multi-policy optimization in agent-based systems. In this poster we propose the use of DWL for decentra...
Representing agent policies compactly is essential for improving the scalability of multi-agent planning algorithms. In this paper, we focus on developing a pruning technique that...