Iteratively Building Virtual Creatures in Minecraft
"Creatures" is a stretch given that the environment is Minecraft, but the idea is simple: iteratively add blocks conditionally (tensor convolution) on the current environment (blocks) to maximize some reward. In this case I use PPO RL to train creatures to touch a glowstone block but you can adapt it to use any algorithm and reward (easily, as it uses the Ray framework). What I like about this work: iteratively finding solutions has a long and colorful history of doing things well: gradient boosting, ResNets, Stable Diffusion, etc. We're after some end optimal state and usually try to get…
In plain words
This project trains AI-controlled creatures in Minecraft to reach goals by iteratively adding blocks based on their environment. Using reinforcement learning algorithms like PPO, the system builds structures step-by-step to maximize rewards, such as touching a glowstone block. Built on the Ray framework, it supports various algorithms and custom rewards. The iterative approach mirrors successful techniques in machine learning like gradient boosting and Stable Diffusion, allowing solutions to improve progressively rather than attempting direct optimization.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
"Creatures" is a stretch given that the environment is Minecraft, but the idea is simple: iteratively add blocks conditionally (tensor convolution) on the current environment (blocks) to maximize some reward. In this case I use PPO RL to train creatures to touch a glowstone block but you can adapt it to use any algorithm and reward (easily, as it uses the Ray framework). What I like about this work: iteratively finding solutions has a long and colorful history of doing things well: gradient boosting, ResNets, Stable Diffusion, etc. We're after some end optimal state and usually try to get right to it via some flavor of SGD. Baking in improvements as part of the problem structure is helpful. I like to think of this as solving the derivative of the solution with respect to time and then integrating over time. The Minecraft environment naturally prevents overfitting because you can spawn creatures in a diverse array of environments and train one policy over them all. What I don't like about this work: Minecraft was chosen for computational reasons but doesn't make cool creatures that walk around and look like cheetahs or whatever. I've compared it against nothing, but it works real good! <g>. Videos in the README. You can install / run with Docker and observe metrics with Tensorboard. Should be plug and play. If not comment. Enjoy!
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, March 2024
the whole month →
- 3Y
Life & fun · 2024 · github.com
Microlaunch▲1,116Launch and get feedback on both the idea and product
Dev tools · 2024 · microlaunch.net
