Image for post
Image for post

Pitting Game-Playing Agent Against Game-Designing Agent

Overview of the paper “Fully Differentiable Procedural Content Generation through Generative Playing Networks” by Bontrager et al.

Chintan Trivedi
Jul 9 · 2 min read

In an earlier article, I had shared a Procedural Content Generation (PCG) paper that showed how we can use Reinforcement Learning to train an agent that can design game levels, instead of playing them. Once this agent designs a game level, the quality of that level was evaluated using a hand-crafted method, which made it cumbersome to apply this method to multiple different games.

Image for post
Image for post
Learning Game-Level Generation with reinforcement Learning. [source]

So today, I want to share a follow-up paper from the same research group which is titled “Fully Differentiable Procedural Content Generation through Generative Playing Networks” by P. Bontrager and J. Togelius. The key difference in this paper is that it simultaneously trains a game-playing RL agent and a game level-generating agent where both agents are in a symbiotic relationship.

The RL agent tries to learn how to win the game by successfully completing a game level and the generator agent provides it increasingly difficult game levels to complete. Here, the reinforcement learning method used is of an Actor-Critic setup, where the Actor network learns what actions to take in the current situation, and the Critic network learns to evaluate the difficulty of the agent’s situation in the current game. This architecture is important because the Critic network is central to the evaluation process which helps the Generator to produce more and more challenging game levels.

Image for post
Image for post
Results from the Generative Playing Network.

This is an innovative paradigm shift in procedural content generation because it allows us to simultaneously train agents that can learn to both design and play a game. This means we know the difficulty level of artificially generated game levels, and based on this information we can automatically generate new levels which are fun and challenging for humans to play with.

Thank you for reading. If you liked this article, you may follow more of my work on Medium, GitHub, or subscribe to my YouTube channel.

deepgamingai

Deep Learning Research for Game Development

Chintan Trivedi

Written by

AI, ML for Digital Games Researcher. Founder at DG AI Research Lab, India. Visit our publication homepage medium.com/deepgamingai for weekly AI & Games content!

deepgamingai

Deep Learning is advancing at an unreal pace and has the potential to revolutionize the games industry. This publication aims to deliver weekly updates on latest research papers and AI projects highlighting it’s applications to this field.

Chintan Trivedi

Written by

AI, ML for Digital Games Researcher. Founder at DG AI Research Lab, India. Visit our publication homepage medium.com/deepgamingai for weekly AI & Games content!

deepgamingai

Deep Learning is advancing at an unreal pace and has the potential to revolutionize the games industry. This publication aims to deliver weekly updates on latest research papers and AI projects highlighting it’s applications to this field.

Medium is an open platform where 170 million readers come to find insightful and dynamic thinking. Here, expert and undiscovered voices alike dive into the heart of any topic and bring new ideas to the surface. Learn more

Follow the writers, publications, and topics that matter to you, and you’ll see them on your homepage and in your inbox. Explore

If you have a story to tell, knowledge to share, or a perspective to offer — welcome home. It’s easy and free to post your thinking on any topic. Write on Medium

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store