Conference Proceedings

Statistical Data Cleaning for Deep Learning of Automation Tasks from Demonstrations

Human demonstrators of deep learning tasks are prone to inconsistencies and errors that can delay or degrade learning. We improve task performance by characterizing supervisor inconsistency and correcting for it using data cleaning techniques. In human demonstrations of a planar part extraction task on a 2DOF robot, trained CNN models show an improvement of 11.2% in mean absolute success rate after data cleaning.

Caleb Chuck, Michael Laskey, Sanjay Krishnan, Ruta Joshi, Roy Fox, and Ken Goldberg, CASE, 2017

Minimum-Information LQG Control — Part I: Memoryless Controllers

We consider the problem of controlling a linear system with Gaussian noise and quadratic cost (LQG), using a memoryless controller that has limited capacity of the channel connecting its sensor to its actuator. We formulate this setting as a sequential rate-distortion (SRD) problem, where we minimize the rate of information required for the controller’s operation, under a constraint on its external cost. We present the optimality principle, and study the interesting and useful phenomenology of the optimal controller, such as the principled reduction of its order.

Roy Fox and Naftali Tishby, CDC, 2016

Minimum-Information LQG Control — Part II: Retentive Controllers

We consider the case where the controller is retentive (memory-utilizing). We can view the memory reader as one more sensor, and the memory writer as one more actuator. We can then formulate the problem of control under communication limitations, again as a sequential rate-distortion (SRD) problem of minimizing the rate of information required for the controller’s operation, under a constraint on its external cost. We show that this problem can be reduced to the memoryless case, studied in Part I. We then further investigate the form of the resulting optimal solution, and demonstrate its interesting phenomenology.

Roy Fox and Naftali Tishby, CDC, 2016


Information-Theoretic Methods for Planning and Learning in Partially Observable Markov Decision Processes

We formulate the problem of optimizing an agent under both extrinsic and intrinsic constraints on its operation in a dynamical system and develop the main tools for solving it. We identify the challenging convergence properties of the optimization algorithm, such as the bifurcation structure of the update operator near phase transitions. We study the special case of linear-Gaussian dynamics and quadratic cost (LQG), where the optimal solution has a particularly simple and solvable form. We also explore the learning task, where the model of the world dynamics is unknown and sample-based updates are used instead.

Roy Fox, PhD Thesis, 2016