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 Matthew E. Taylor

The Atari Data Scraper


Apr 11, 2021
Brittany Davis Pierson, Justine Ventura, Matthew E. Taylor

* 3 authors, nine pages, 6 figures, papers with code 

  Access Paper or Ask Questions

The Effect of Q-function Reuse on the Total Regret of Tabular, Model-Free, Reinforcement Learning


Mar 07, 2021
Volodymyr Tkachuk, Sriram Ganapathi Subramanian, Matthew E. Taylor

* 7 pages, 2 figures, submitted to ALA 2021 

  Access Paper or Ask Questions

Model-Invariant State Abstractions for Model-Based Reinforcement Learning


Feb 19, 2021
Manan Tomar, Amy Zhang, Roberto Calandra, Matthew E. Taylor, Joelle Pineau


  Access Paper or Ask Questions

Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systems


Feb 16, 2021
Yaodong Yang, Jun Luo, Ying Wen, Oliver Slumbers, Daniel Graves, Haitham Bou Ammar, Jun Wang, Matthew E. Taylor

* AAMAS 2021 

  Access Paper or Ask Questions

Improving Reinforcement Learning with Human Assistance: An Argument for Human Subject Studies with HIPPO Gym


Feb 02, 2021
Matthew E. Taylor, Nicholas Nissen, Yuan Wang, Neda Navidi


  Access Paper or Ask Questions

HAMMER: Multi-Level Coordination of Reinforcement Learning Agents via Learned Messaging


Jan 18, 2021
Nikunj Gupta, G Srinivasaraghavan, Swarup Kumar Mohalik, Matthew E. Taylor


  Access Paper or Ask Questions

Useful Policy Invariant Shaping from Arbitrary Advice


Nov 02, 2020
Paniz Behboudian, Yash Satsangi, Matthew E. Taylor, Anna Harutyunyan, Michael Bowling

* 9 pages, 6 figures, Adaptive and Learning Agents (ALA) 2020 Workshop 

  Access Paper or Ask Questions

Maximum Reward Formulation In Reinforcement Learning


Oct 08, 2020
Sai Krishna Gottipati, Yashaswi Pathak, Rohan Nuttall, Sahir, Raviteja Chunduru, Ahmed Touati, Sriram Ganapathi Subramanian, Matthew E. Taylor, Sarath Chandar

* 13 pages, 5 figures 

  Access Paper or Ask Questions

Lucid Dreaming for Experience Replay: Refreshing Past States with the Current Policy


Sep 29, 2020
Yunshu Du, Garrett Warnell, Assefaw Gebremedhin, Peter Stone, Matthew E. Taylor

* 20 pages (with appendices), 5 figures, preprint 

  Access Paper or Ask Questions

A Conceptual Framework for Externally-influenced Agents: An Assisted Reinforcement Learning Review


Jul 03, 2020
Adam Bignold, Francisco Cruz, Matthew E. Taylor, Tim Brys, Richard Dazeley, Peter Vamplew, Cameron Foale

* 33 pages, 8 figures 

  Access Paper or Ask Questions

Work in Progress: Temporally Extended Auxiliary Tasks


Apr 16, 2020
Craig Sherstan, Bilal Kartal, Pablo Hernandez-Leal, Matthew E. Taylor

* Accepted for the Adaptive and Learning Agents (ALA) Workshop at AAMAS 2020 

  Access Paper or Ask Questions

Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey


Mar 10, 2020
Sanmit Narvekar, Bei Peng, Matteo Leonetti, Jivko Sinapov, Matthew E. Taylor, Peter Stone


  Access Paper or Ask Questions

Multi Type Mean Field Reinforcement Learning


Mar 09, 2020
Sriram Ganapathi Subramanian, Pascal Poupart, Matthew E. Taylor, Nidhi Hegde

* Paper to appear in the Proceedings of International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS) 2020. Revised version has some typos corrected 

  Access Paper or Ask Questions

On Hard Exploration for Reinforcement Learning: a Case Study in Pommerman


Jul 26, 2019
Chao Gao, Bilal Kartal, Pablo Hernandez-Leal, Matthew E. Taylor

* AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE) 2019 

  Access Paper or Ask Questions

Action Guidance with MCTS for Deep Reinforcement Learning


Jul 25, 2019
Bilal Kartal, Pablo Hernandez-Leal, Matthew E. Taylor

* AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE'19). arXiv admin note: substantial text overlap with arXiv:1904.05759, arXiv:1812.00045 

  Access Paper or Ask Questions

Terminal Prediction as an Auxiliary Task for Deep Reinforcement Learning


Jul 24, 2019
Bilal Kartal, Pablo Hernandez-Leal, Matthew E. Taylor

* AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE'19). arXiv admin note: text overlap with arXiv:1812.00045 

  Access Paper or Ask Questions

Agent Modeling as Auxiliary Task for Deep Reinforcement Learning


Jul 22, 2019
Pablo Hernandez-Leal, Bilal Kartal, Matthew E. Taylor

* AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE'19) 

  Access Paper or Ask Questions

Interactive Learning of Environment Dynamics for Sequential Tasks


Jul 19, 2019
Robert Loftin, Bei Peng, Matthew E. Taylor, Michael L. Littman, David L. Roberts


  Access Paper or Ask Questions

Skynet: A Top Deep RL Agent in the Inaugural Pommerman Team Competition


Apr 20, 2019
Chao Gao, Pablo Hernandez-Leal, Bilal Kartal, Matthew E. Taylor

* 4th Multidisciplinary Conference on Reinforcement Learning and Decision Making 

  Access Paper or Ask Questions

Safer Deep RL with Shallow MCTS: A Case Study in Pommerman


Apr 10, 2019
Bilal Kartal, Pablo Hernandez-Leal, Chao Gao, Matthew E. Taylor

* Adaptive Learning Agents (ALA) Workshop at AAMAS 2019. arXiv admin note: substantial text overlap with arXiv:1812.00045 

  Access Paper or Ask Questions

Jointly Pre-training with Supervised, Autoencoder, and Value Losses for Deep Reinforcement Learning


Apr 03, 2019
Gabriel V. de la Cruz Jr., Yunshu Du, Matthew E. Taylor

* Accepted in Adaptive and Learning Agents (ALA) Workshop at AAMAS 

  Access Paper or Ask Questions

Pre-training with Non-expert Human Demonstration for Deep Reinforcement Learning


Dec 21, 2018
Gabriel V. de la Cruz, Yunshu Du, Matthew E. Taylor


  Access Paper or Ask Questions

Using Monte Carlo Tree Search as a Demonstrator within Asynchronous Deep RL


Nov 30, 2018
Bilal Kartal, Pablo Hernandez-Leal, Matthew E. Taylor

* 9 pages, 6 figures, To appear at AAAI-19 Workshop on Reinforcement Learning in Games 

  Access Paper or Ask Questions

Autonomous Extraction of a Hierarchical Structure of Tasks in Reinforcement Learning, A Sequential Associate Rule Mining Approach


Nov 17, 2018
Behzad Ghazanfari, Fatemeh Afghah, Matthew E. Taylor

* arXiv admin note: text overlap with arXiv:1709.04579 

  Access Paper or Ask Questions

Is multiagent deep reinforcement learning the answer or the question? A brief survey


Oct 12, 2018
Pablo Hernandez-Leal, Bilal Kartal, Matthew E. Taylor

* Under review since Oct 2018 

  Access Paper or Ask Questions