Matthew W. Robards

Sparse Kernel-SARSA(λ) with an Eligibility Trace

Scott Sanner, Peter Sunehag, Bhaskara Marthi, 2011, ECML/PKDD.

Wearable sensor activity analysis using semi-Markov models with a grammar

Alexander J. Smola, Peter Sunehag, Gideon Dror, 2010, Pervasive Mob. Comput..

Semi-Markov kMeans Clustering and Activity Recognition from Body-Worn Sensors

Peter Sunehag, Matthew W. Robards, 2009, 2009 Ninth IEEE International Conference on Data Mining.

Gradient Based Algorithms with Loss Functions and Kernels for Improved On-Policy Control

Peter Sunehag, Matthew W. Robards, 2011, EWRL.

Proposal Review : “ Reinforcement Learning for Large Continuous Spaces ”

Matthew W. Robards, 2009 .

Near Optimal On-Policy Control

Matthew W. Robards, Peter Sunehag, 2011 .

Loss Functions For Improved On-Policy Control

Matthew W. Robards, Peter Sunehag, 2011 .