Главная
Study mode:
on
1
- Intro & Overview
2
- Level Design via Reinforcement Learning
3
- Reinforcement Learning
4
- Observation Space
5
- Action Space
6
- Change Percentage Limit
7
- Quantitative Results
8
- Conclusion & Outlook
Description:
Explore a novel approach to procedural content generation in games through this video explanation of the paper "PCGRL: Procedural Content Generation via Reinforcement Learning." Dive into how deep reinforcement learning can be applied to game level creation, framing level design as a sequential decision-making process. Learn about the observation space, action space, and change percentage limit in this innovative method. Discover how this approach results in a fast and diverse level generator, even when few or no examples exist for training. Examine the quantitative results and gain insights into the future implications of using reinforcement learning for content generation in gaming.

PCGRL - Procedural Content Generation via Reinforcement Learning - Paper Explained

Yannic Kilcher
Add to list
0:00 / 0:00