John W. Roberts - researchr alias

researchr

You are not signed in
Sign in
Sign up

Viewing Publication 1 - 9 from 9

2013

Reinforcement learning with misspecified model classesJoshua Mason Joseph, Alborz Geramifard, John W. Roberts, Jonathan P. How, Nicholas Roy. icra 2013: 939-946 [doi]

2011

Feedback controller parameterizations for Reinforcement LearningJohn W. Roberts, Ian R. Manchester, Russ Tedrake. adprl 2011: 310-317 [doi]

2010

Motor Learning at Intermediate Reynolds Number: Experiments with Policy Gradient on the Flapping Flight of a Rigid WingJohn W. Roberts, Lionel Moret, Jun Zhang, Russ Tedrake. In Olivier Sigaud, Jan Peters, editors, From Motor Learning to Interaction Learning in Robots. Volume 264 of Studies in Computational Intelligence, pages 293-309, Springer, 2010. [doi]

LQR-trees: Feedback Motion Planning via Sums-of-Squares VerificationRuss Tedrake, Ian R. Manchester, Mark Tobenkin, John W. Roberts. ijrr, 29(8):1038-1052, 2010. [doi]

2009

On the controllability of fixed-wing perchingJohn W. Roberts, Rick Cory, Russ Tedrake. amcc 2009: 2018-2023 [doi]

2008

Signal-to-Noise Ratio Analysis of Policy Gradient AlgorithmsJohn W. Roberts, Russ Tedrake. nips 2009: 1361-1368 [doi]

1990

Multiprocessor Performance-Measurement InstrumentationAlan Mink, Robert J. Carpenter, George Nacht, John W. Roberts. Computer, 23(9):63-75, 1990.

1989

Hybrid Performance Measurement Instrumentation for Loosely-Cpupled MIMD ArchitecturesJohn W. Roberts, John Antonishek, Alan Mink. sigmetrics 1989: 239

1987

Hardware-Assisted Multiprocessor Performance MeasurementAlan Mink, Jesse M. Draper, John W. Roberts, Robert J. Carpenter. performance 1988: 151-168

Sign in or sign up to see more results.

runs on WebDSL