Backpropagating through a maze with candle and WASM
Loading WASM module... Width: Height: Wall Density: Learning Rate: Max Steps: Generate & Optimize This demo uses gradient descent to solve a discrete maze. Try playing with the hyperparameters to see how they affect the optimization process! No neural network involved: logits are directly optimized, from a random initialization, for each maze. This runs entirely on your local device, thanks to candle and Rust's support for WebAssembly. You can disconnect from the Internet after loading this