Faster Policy Learning with Continuous-Time Gradients

3 code implementations • 12 Dec 2020 • Samuel Ainsworth, Kendall Lowrey, John Thickstun, Zaid Harchaoui, Siddhartha Srinivasa

We study the estimation of policy gradients for continuous-time systems with known dynamics.

Mosaic: A Sample-Based Database System for Open World Query Processing

no code implementations • 17 Dec 2019 • Laurel Orr, Samuel Ainsworth, Walter Cai, Kevin Jamieson, Magda Balazinska, Dan Suciu

Recently, with the increase in the number of public data repositories, sample data has become easier to access.

Mo' States Mo' Problems: Emergency Stop Mechanisms from Observation

1 code implementation • NeurIPS 2019 • Samuel Ainsworth, Matt Barnes, Siddhartha Srinivasa

In many environments, only a relatively small subset of the complete state space is necessary in order to accomplish a given task.

reinforcement-learning Reinforcement Learning (RL)

Interpretable VAEs for nonlinear group factor analysis

no code implementations • 17 Feb 2018 • Samuel Ainsworth, Nicholas Foti, Adrian KC Lee, Emily Fox

Deep generative models have recently yielded encouraging results in producing subjectively realistic samples of complex data.

Interactive Preference Learning of Utility Functions for Multi-Objective Optimization

no code implementations • 14 Dec 2016 • Ian Dewancker, Michael McCourt, Samuel Ainsworth

Real-world engineering systems are typically compared and contrasted using multiple metrics.

Optimization and Control 90C29, 90B50