Voyager Applications, MineDojo, and DeepMind

Welcome to our weekly newsletter and platform update! Every week we’ll bring you the latest AI + gaming news, resources, and updates from the Regression Games team.

Join our community on Discord and start playing!

Weekly Spotlight - MineDojo

With the number of papers and approaches this group has published around Minecraft agents, it’s about time we share them directly! Known for their projects such as Voyager and MineCLIP, the MineDojo project has a great set of resources and data for getting started with agents in Minecraft. The best Minecraft AI approaches and models typically use their framework and tools. Make sure to check out their documentation page to see how to setup their environments!

Regression Games Platform Update

The Regression Games team has been gearing up for some big updates over the coming weeks. We plan to announce these updates via a public roadmap, as well as on our social media accounts and Discord.

In addition to a roadmap for players and our competitive AI platform, we also have exciting updates regarding initial availability of our platform for studios. We are excited to begin testing our bot-building tools for Unity with studios, and we appreciate those who have given us feedback so far! If you are interested in learning more about our product offer, please email [email protected] to get in touch.

Twitter Post - Parallel Uses Voyager to Write New Bots

In our previous newsletter, we chatted about Voyager, an approach that uses LLMs to rewrite bots for code, which can outperformed RL approaches. Parallel, a Web3 AI game, announced an update where they were able to get Voyager to work on their own game - it’s awesome to see the approach implemented in other games!

Technical Paper of the Week

Our technical paper this week covers yet another ICLR paper, titled “Bigger, Better, Faster: Human-level Atari with human-level efficiency“, brought to you by Google DeepMind. In this paper, they discuss both new approaches and practical design choices that allows their model to not only perform as good or better than the existing RL approaches for playing Atari, but also achieve better computational performance.

Members of our community discuss these papers on our Discord #reading-club channel. You can also find all past resources on our GitHub.

Looking for something new? Join the Regression Games team!

Have feedback about our newsletter? Let us know at [email protected]

You are receiving this email because you registered to our mailing list or are a player on our platform.