Mike Preuß

MCTS/EA hybrid GVGAI players and game difficulty estimation

2016

In the General Video Game Playing competitions of the last years, Monte-Carlo tree search as well as Evolutionary Algorithm based controllers have been successful. However, both approaches have certain weaknesses, suggesting that certain hybrids could …

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

2020 · 2020 IEEE Conference on Games (CoG)

The Obstacle Tower Challenge is the task to master a procedurally generated chain of levels that subsequently get harder to complete. Whereas the most top performing entries of last year's competition used human demonstrations or …

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

2020 · arXiv (Cornell University)

Deep reinforcement learning has shown remarkable success in the past few years. Highly complex sequential decision making problems have been solved in tasks such as game playing and robotics. Unfortunately, the sample complexity of most …

Impressions of the GDMC AI Settlement Generation Challenge in Minecraft

2021 · arXiv (Cornell University)

The GDMC AI settlement generation challenge is a PCG competition about producing an algorithm that can create an "interesting" Minecraft settlement for a given map. This paper contains a collection of written experiences with this …

Agentic Large Language Models, a Survey

2025 · Journal of Artificial Intelligence Research

Background: There is great interest in agentic LLMs, large language models that act as agents. Objectives: We review the growing body of work in this area and provide a research agenda. Methods: Agentic LLMs are …