Matthew J. Hausknecht

Sort by:

Beyond short snippets: Deep networks for video classification

Joe Yue-Hei Ng, Matthew J. Hausknecht, Sudheendra Vijayanarasimhan, Oriol Vinyals, Rajat Monga, George Toderici
IEEE Conference on Computer Vision and Pattern…
2015

Convolutional neural networks (CNNs) have been extensively applied for image recognition problems giving state-of-the-art results on recognition, detection, segmentation and retrieval. In this work… (More)

Deep Recurrent Q-Learning for Partially Observable MDPs

Matthew J. Hausknecht, Peter Stone
AAAI Fall Symposia
2015

Deep Reinforcement Learning has yielded proficient controllers for complex tasks. However, these controllers have limited memory and rely on being able to perceive the complete game screen at each… (More)

Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents

Marlos C. Machado, Marc G. Bellemare, Erik Talvitie, Joel Veness, Matthew J. Hausknecht, Michael H. Bowling
IJCAI
2018

The Arcade Learning Environment (ALE) is an evaluation platform that poses the challenge of building AI agents with general competency across dozens of Atari 2600 games. It supports a variety of… (More)

Deep Reinforcement Learning in Parameterized Action Space

Recent work has shown that deep neural networks are capable of approximating both value functions and policies in reinforcement learning domains featuring continuous state and action spaces. However,… (More)

A Neuroevolution Approach to General Atari Game Playing

Matthew J. Hausknecht, Joel Lehman, Risto Miikkulainen, Peter Stone
IEEE Transactions on Computational Intelligence…
2014

This paper addresses the challenge of learning to play many different video games with little domain-specific knowledge. Specifically, it introduces a neuroevolution approach to general Atari 2600… (More)

HyperNEAT-GGP: a hyperNEAT-based atari general game player

Matthew J. Hausknecht, Piyush Khandelwal, Risto Miikkulainen, Peter Stone
GECCO
2012

This paper considers the challenge of enabling agents to learn with as little domain-specific knowledge as possible. The main contribution is HyperNEAT-GGP, a HyperNEAT-based General Game Playing… (More)

TextWorld: A Learning Environment for Text-based Games

Marc-Alexandre Côté, Ákos Kádár, +9 authors Adam Trischler
ArXiv
2018

We introduce TextWorld, a sandbox learning environment for the training and evaluation of RL agents on text-based games. TextWorld is a Python library that handles interactive playthrough of text… (More)

For want of a nail: How absences cause events.

Phillip Wolff, Aron K. Barbey, Matthew J. Hausknecht
Journal of experimental psychology. General
2010

Causation by omission is instantiated when an effect occurs from an absence, as in The absence of nicotine causes withdrawal or Not watering the plant caused it to wilt. The phenomenon has been… (More)

Leveraging Grammar and Reinforcement Learning for Neural Program Synthesis

Rudy R. Bunel, Matthew J. Hausknecht, Jacob Devlin, Rishabh Singh, Pushmeet Kohli
ICLR
2018

Program synthesis is the task of automatically generating a program consistent with a specification. Recent years have seen proposal of a number of neural approaches for program synthesis, many of… (More)

Learning Powerful Kicks on the Aibo ERS-7: The Quest for a Striker

Machine learning applied to optimize kick power entirely on the real robot – Aibo ERS-7. • Learned kick significantly more powerful than UT Austin Villa’s best hand-coded kick. • Model inversion to… (More)

Filter Results:

Publication Year

Publication Type

Co-author

Journals and Conferences