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…
Iteratively Building Virtual Creatures in Minecraft launched on March 20, 2024 with 49 votes, #1,019 of 4,270 launches that month and more than 90% of that year's launches. The site was still online in September 2026, 2 years on.
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
Grow virtual creatures in static and physics simulated environments. - cfusting/conditional-growth
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…
Does a similar job
all alternatives →- BPBeating Pokemon Red with RL and <10M Parameters2025 · drubinstein.github.io · ▲183
Hi everyone! After spending hundreds of hours, we're excited to finally share our progress in developing a reinforcement learning system to beat Pokémon Red. Our system successfully completes the game using a policy under 10M parameters, PPO, and a few novel techniques. With the release of Claude Plays Pokémon, now feels like the perfect time to showcase our work. We'd love to get feedback!
Watch a neural net learn to play SnakeMay 2026 · ppo.gradexp.xyz · ▲205In browser PPO training demo, made possible by tinygrad: TinyJit -> WebGPU kernels. Requires WebGPU.
Visual A* pathfinding and maze generation in Python2024 · github.com · ▲135I was fascinated reading through another recent HN submission about a highly efficient implementation of A* in Lisp, which got me thinking about how I could do something similar in Python. However, these kinds of pathfinding algorithms really need complex terrain/mazes with interesting obstructions to showcase what they can do and how they work. So, I started thinking about how I could generate cool and diverse random "mazes" (they aren't really mazes, but I'm not sure what the best term is). I got a bit carried away thinking of lots of different cool ways to generate these mazes, such…
ML Blocks – Deploy multimodal AI workflows without code2024 · mlblocks.com · ▲112Hey everyone, ML Blocks is a node-based workflow builder to create multi-modal AI workflows without writing any code. You connect blocks that call various visual models like GPT4v, Segment Anything, Dino etc. along with basic image processing blocks like resize, invert color, blur, crop, and several others. The idea is to make it easier to deploy multi-step image processing workflows, without needing to spin up endless custom OpenCV cloud functions to glue together AI models. Usually, even if you're using cloud inference servers like Replicate, you still need to write your own image…
- ANA new A.I. Algorithm for Polygonal Mesh Mazes2012 · petercottle.com · ▲101
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 29d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, March 2024
the whole month →
🌐 The Internet Computer! Free, Open-Source, and Self-Hostable. - HeyPuter/puter
Dev tools · 2024 · github.com
Microlaunch▲1,115Launch and get feedback on both the idea and product
Dev tools · 2024 · microlaunch.net
