J
James Andrew Bagnell
Researcher at Carnegie Mellon University
Publications - 31
Citations - 2835
James Andrew Bagnell is an academic researcher from Carnegie Mellon University. The author has contributed to research in topics: Mobile robot & Overhead (computing). The author has an hindex of 21, co-authored 31 publications receiving 2548 citations. Previous affiliations of James Andrew Bagnell include Uber .
Papers
More filters
Book ChapterDOI
Activity forecasting
TL;DR: In this article, the authors address the task of inferring the future actions of people from noisy visual input by using state-of-the-art semantic scene understanding combined with ideas from optimal control theory.
Book ChapterDOI
Pose Machines: Articulated Pose Estimation via Inference Machines
TL;DR: This paper builds upon the inference machine framework and presents a method for articulated human pose estimation that incorporates rich spatial interactions among multiple parts and information across parts of different scales and outperforms the state-of-the-art on these benchmarks.
Proceedings ArticleDOI
Modeling Interaction via the Principle of Maximum Causal Entropy
TL;DR: This work presents the principle of maximum causal entropy—an approach based on causally conditioned probabilities that can appropriately model the availability and influence of sequentially revealed side information.
Proceedings Article
Policy Search by Dynamic Programming
TL;DR: If a "baseline distribution" is given (indicating roughly how often the authors expect a good policy to visit each state), then a policy search algorithm is derived that terminates in a finite number of steps, and for which the author can provide non-trivial performance guarantees.
Proceedings ArticleDOI
Boosting Structured Prediction for Imitation Learning
TL;DR: A novel approach, MMPBOOST, is provided, based on the functional gradient descent view of boosting, that extends MMP by "boosting" in new features by using simple binary classification or regression to improve performance of MMP imitation learning.