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 Mike Preuss

Potential-based Reward Shaping in Sokoban


Sep 10, 2021
Zhao Yang, Mike Preuss, Aske Plaat


  Access Paper or Ask Questions

High-Accuracy Model-Based Reinforcement Learning, a Survey


Jul 17, 2021
Aske Plaat, Walter Kosters, Mike Preuss

* arXiv admin note: text overlap with arXiv:2008.05598 

  Access Paper or Ask Questions

Procedural Content Generation: Better Benchmarks for Transfer Reinforcement Learning


May 31, 2021
Matthias Müller-Brockhausen, Mike Preuss, Aske Plaat


  Access Paper or Ask Questions

Transfer Learning and Curriculum Learning in Sokoban


May 25, 2021
Zhao Yang, Mike Preuss, Aske Plaat


  Access Paper or Ask Questions

Adaptive Warm-Start MCTS in AlphaZero-like Deep Reinforcement Learning


May 13, 2021
Hui Wang, Mike Preuss, Aske Plaat


  Access Paper or Ask Questions

An Analysis of Phenotypic Diversity in Multi-Solution Optimization


May 10, 2021
Alexander Hagg, Mike Preuss, Alexander Asteroth, Thomas Bäck


  Access Paper or Ask Questions

Applications of Artificial Intelligence in Live Action Role-Playing Games (LARP)


Aug 25, 2020
Christoph Salge, Emily Short, Mike Preuss, Spyridion Samothrakis, Pieter Spronck

* 8 pages, 2 figures. Published at IEEE Conference on Games, 2020 

  Access Paper or Ask Questions

Model-Based Deep Reinforcement Learning for High-Dimensional Problems, a Survey


Aug 11, 2020
Aske Plaat, Walter Kosters, Mike Preuss


  Access Paper or Ask Questions

Tackling Morpion Solitaire with AlphaZero-likeRanked Reward Reinforcement Learning


Jun 14, 2020
Hui Wang, Mike Preuss, Michael Emmerich, Aske Plaat

* 4 pages, 2 figures. the first/ongoing attempt to tackle Morpion Solitaire using ranked reward reinforcement learning. submitted to SYNASC2020 

  Access Paper or Ask Questions

Versatile Black-Box Optimization


Apr 29, 2020
Jialin Liu, Antoine Moreau, Mike Preuss, Baptiste Roziere, Jeremy Rapin, Fabien Teytaud, Olivier Teytaud

* Accepted at GECCO 2020 

  Access Paper or Ask Questions

Warm-Start AlphaZero Self-Play Search Enhancements


Apr 26, 2020
Hui Wang, Mike Preuss, Aske Plaat


  Access Paper or Ask Questions

Obstacle Tower Without Human Demonstrations: How Far a Deep Feed-Forward Network Goes with Reinforcement Learning


Apr 01, 2020
Marco Pleines, Jenia Jitsev, Mike Preuss, Frank Zimmer

* 8 pages, 9 figures, 2 tables, under review 

  Access Paper or Ask Questions

A New Challenge: Approaching Tetris Link with AI


Apr 01, 2020
Matthias Muller-Brockhausen, Mike Preuss, Aske Plaat


  Access Paper or Ask Questions

Analysis of Hyper-Parameters for Small Games: Iterations or Epochs in Self-Play?


Mar 12, 2020
Hui Wang, Michael Emmerich, Mike Preuss, Aske Plaat


  Access Paper or Ask Questions

From Chess and Atari to StarCraft and Beyond: How Game AI is Driving the World of AI


Feb 24, 2020
Sebastian Risi, Mike Preuss

* KI - Kuenstliche Intelligenz (2020) 

  Access Paper or Ask Questions

Hyper-Parameter Sweep on AlphaZero General


Mar 19, 2019
Hui Wang, Michael Emmerich, Mike Preuss, Aske Plaat

* 19 pages 13 figures 

  Access Paper or Ask Questions

Learning to Plan Chemical Syntheses


Aug 14, 2017
Marwin H. S. Segler, Mike Preuss, Mark P. Waller

* Nature 555 (2018), 604-610 

  Access Paper or Ask Questions

The True Destination of EGO is Multi-local Optimization


Apr 19, 2017
Simon Wessing, Mike Preuss


  Access Paper or Ask Questions