We present four new reinforcement learning algorithms based on actor-critic and natural-gradient ideas, and provide their convergence proofs. Actor-critic reinforcement learning m...
Shalabh Bhatnagar, Richard S. Sutton, Mohammad Gha...
L1 regularized logistic regression is now a workhorse of machine learning: it is widely used for many classification problems, particularly ones with many features. L1 regularized...
Su-In Lee, Honglak Lee, Pieter Abbeel, Andrew Y. N...
In this paper we describe an extractive method of creating very short summaries or gists that capture the essence of a news story using a linguistic technique called lexical chaini...
Nicola Stokes, Eamonn Newman, Joe Carthy, Alan F. ...
Many organizations have embraced intranets with the intent to harness the technology to support knowledge management initiatives. Despite the promise that intranet technology hold...
We present a critique of language-based modelling for text input research, and propose an alternative inputbased approach. Current language-based statistical models are derived fr...