Search Results for author: Wolfgang Konen

Found 10 papers, 1 papers with code

Improving Reinforcement Learning Efficiency with Auxiliary Tasks in Non-Visual Environments: A Comparison

no code implementations6 Oct 2023 Moritz Lange, Noah Krystiniak, Raphael C. Engelhardt, Wolfgang Konen, Laurenz Wiskott

These insights can inform future development of interpretable representation learning approaches for non-visual observations and advance the use of RL solutions in real-world scenarios.

Continuous Control reinforcement-learning +2

Towards Learning Rubik's Cube with N-tuple-based Reinforcement Learning

no code implementations28 Jan 2023 Wolfgang Konen

This work describes in detail how to learn and solve the Rubik's cube game (or puzzle) in the General Board Game (GBG) learning and playing framework.

reinforcement-learning Reinforcement Learning (RL) +1

AlphaZero-Inspired Game Learning: Faster Training by Using MCTS Only at Test Time

1 code implementation28 Apr 2022 Johannes Scheiermann, Wolfgang Konen

Recently, the seminal algorithms AlphaGo and AlphaZero have started a new era in game learning and deep reinforcement learning.

Rubik's Cube

Final Adaptation Reinforcement Learning for N-Player Games

no code implementations29 Nov 2021 Wolfgang Konen, Samineh Bagheri

Our main contribution is that FARL is a vitally important ingredient to achieve success with the player-centered view in various games.

Board Games Q-Learning +2

General Board Game Playing for Education and Research in Generic AI Game Learning

no code implementations11 Jul 2019 Wolfgang Konen

On various games, TD($\lambda$)-n-tuple is found to be superior to other generic agents like MCTS.

Board Games

SACOBRA with Online Whitening for Solving Optimization Problems with High Conditioning

no code implementations17 Apr 2019 Samineh Bagheri, Wolfgang Konen, Thomas Bäck

We show on a set of high-conditioning functions that online whitening tackles SACOBRA's early stagnation issue and reduces the optimization error by a factor between 10 to 1e12 as compared to the plain SACOBRA, though it imposes many extra function evaluations.

Vocal Bursts Intensity Prediction

Solving the G-problems in less than 500 iterations: Improved efficient constrained optimization by surrogate modeling and adaptive parameter control

no code implementations31 Dec 2015 Samineh Bagheri, Wolfgang Konen, Michael Emmerich, Thomas Bäck

We analyze the importance of the several new elements in SACOBRA and find that each element of SACOBRA plays a role to boost up the overall optimization performance.

Cannot find the paper you are looking for? You can Submit a new open access paper.