Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Tim Klinger

Consolidation via Policy Information Regularization in Deep RL for Multi-Agent Games


Nov 23, 2020
Tyler Malloy, Tim Klinger, Miao Liu, Matthew Riemer, Gerald Tesauro, Chris R. Sims


  Access Paper or Ask Questions

Deep RL With Information Constrained Policies: Generalization in Continuous Control


Oct 09, 2020
Tyler Malloy, Chris R. Sims, Tim Klinger, Miao Liu, Matthew Riemer, Gerald Tesauro


  Access Paper or Ask Questions

A Study of Compositional Generalization in Neural Models


Jul 08, 2020
Tim Klinger, Dhaval Adjodah, Vincent Marois, Josh Joseph, Matthew Riemer, Alex 'Sandy' Pentland, Murray Campbell

* 28 pages 

  Access Paper or Ask Questions

Finding Macro-Actions with Disentangled Effects for Efficient Planning with the Goal-Count Heuristic


Apr 28, 2020
Cameron Allen, Tim Klinger, George Konidaris, Matthew Riemer, Gerald Tesauro

* Code available at https://github.com/camall3n/skills-for-planning 

  Access Paper or Ask Questions

Routing Networks and the Challenges of Modular and Compositional Computation


Apr 29, 2019
Clemens Rosenbaum, Ignacio Cases, Matthew Riemer, Tim Klinger


  Access Paper or Ask Questions

Logical Rule Induction and Theory Learning Using Neural Theorem Proving


Sep 12, 2018
Andres Campero, Aldo Pareja, Tim Klinger, Josh Tenenbaum, Sebastian Riedel


  Access Paper or Ask Questions

Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering


Apr 26, 2018
Shuohang Wang, Mo Yu, Jing Jiang, Wei Zhang, Xiaoxiao Guo, Shiyu Chang, Zhiguo Wang, Tim Klinger, Gerald Tesauro, Murray Campbell

* 13 pages 

  Access Paper or Ask Questions

Scalable Recollections for Continual Lifelong Learning


Feb 26, 2018
Matthew Riemer, Tim Klinger, Michele Franceschini, Djallel Bouneffouf


  Access Paper or Ask Questions

Routing Networks: Adaptive Selection of Non-linear Functions for Multi-Task Learning


Dec 31, 2017
Clemens Rosenbaum, Tim Klinger, Matthew Riemer

* Under Review at ICLR 2018 

  Access Paper or Ask Questions

e-QRAQ: A Multi-turn Reasoning Dataset and Simulator with Explanations


Aug 05, 2017
Clemens Rosenbaum, Tian Gao, Tim Klinger

* 7 pages, 3 figures, presented at 2017 ICML Workshop on Human Interpretability in Machine Learning (WHI 2017), Sydney, NSW, Australia 

  Access Paper or Ask Questions

Multiresolution Recurrent Neural Networks: An Application to Dialogue Response Generation


Jun 14, 2016
Iulian Vlad Serban, Tim Klinger, Gerald Tesauro, Kartik Talamadupula, Bowen Zhou, Yoshua Bengio, Aaron Courville

* 21 pages, 2 figures, 10 tables 

  Access Paper or Ask Questions