Mykel J. Kochenderfer

Publications283
h-index39
Citations7,599
Highly Influential Citations684
Author pages are created from data sourced from our academic publisher partnerships and public sources.

Recommended Authors

  • P. Abbeel
  • 560 Publications • 71,785 Citations
  • David Silver
  • 121 Publications • 85,095 Citations
  • Kyle D. Julian
  • 25 Publications • 1,982 Citations
  • Ritchie Lee
  • 33 Publications • 482 Citations
  • Publications
  • Influence
Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks
TLDR
Results show that the novel, scalable, and efficient technique presented can successfully prove properties of networks that are an order of magnitude larger than the largest networks verified using existing methods.
View PDF on arXiv
Cooperative Multi-agent Control Using Deep Reinforcement Learning
TLDR
It is shown that policy gradient methods tend to outperform both temporal-difference and actor-critic methods and that curriculum learning is vital to scaling reinforcement learning algorithms in complex multi-agent domains.
View via Publisher
Decision Making Under Uncertainty: Theory and Application
TLDR
This book provides an introduction to the challenges of decision making under uncertainty from a computational perspective and presents both the theory behind decision making models and algorithms and a collection of example applications that range from speech recognition to aircraft collision avoidance.
View via Publisher
Imitating driver behavior with generative adversarial networks
TLDR
This paper adopts a method for overcoming the problem of cascading errors inherent in prior approaches, resulting in realistic behavior that is robust to trajectory perturbations, and extends Generative Adversarial Imitation Learning to the training of recurrent policies.
View on IEEE
The Marabou Framework for Verification and Analysis of Deep Neural Networks
TLDR
Marabou is an SMT-based tool that can answer queries about a network’s properties by transforming these queries into constraint satisfaction problems, and it performs high-level reasoning on the network that can curtail the search space and improve performance.
View via Publisher
Policy compression for aircraft collision avoidance systems
TLDR
A deep neural network is used to learn a complex non-linear function approximation of the lookup table, which reduces the required storage space by a factor of 1000 and surpasses the original table on the performance metrics and encounter sets evaluated here.
View on IEEE
Robust Airborne Collision Avoidance through Dynamic Programming
TLDR
Simulations demonstrate how a new approach to automatically deriving the optimal logic with respect to a probabilistic model and a set of performance metrics significantly outperforms TCAS according to the standard safety and operational performance metrics.
Common Sense Data Acquisition for Indoor Mobile Robots
TLDR
This work describes the collection of common sense data through the Open Mind Indoor Common Sense website and discusses active desire selection based on current beliefs and commands and a room-labeling application based on probability estimates from the common sense knowledge base.
View Paper
Next-Generation Airborne Collision Avoidance System
Abstract : In response to a series of midair collisions involving commercial airliners, Lincoln Laboratory was directed by the Federal Aviation Administration in the 1970s to participate in the…
Analysis of Recurrent Neural Networks for Probabilistic Modeling of Driver Behavior
TLDR
This paper reveals that the strong performance of recurrent networks is due to the ability of the recurrent network to identify recent trends in the ego-vehicle's state, and recurrent networks are shown to perform as, well as feedforward networks with longer histories as inputs.
View on IEEE
...
...