Training Experiment · HTML

EmblaV2

Extending EmblaV1 for robotic application and biologically inspired intrinsic reward

eze770@eze770 · Atlas 57.9 · #10= builder

What it is

EmblaV2 is a reinforcement learning agent based on DreamerV3 with added intrinsic motivation and self-model components, trained on various Gymnasium environments using PyTorch.

Scored from the code at its last scan, 23 Oct 2026. How merit is scored

Where it counts

Machine Learning90%
AI Agents80%
Computer Vision70%
MLOps20%
Data Science10%

How much of the project is about each field, as scoring counts it. It ranks in the field it is most about.

Around it on the Machine Learning board

Whole board

RankProjectBuilderFieldMerit

12, shared rankvid-factoryML Application · JavaScriptVideo Content Factory is a web application for organizing early-stage content ideas and drafts, featuring a browser-native runtime that operates entirely in the client using WebAssembly and OPFS for persistence, with a fallback FastAPI implementation.62.0/100AdvancedJarad PeckenpaughMachine Learning
14mamba3-atlas-imageAI Developer Tool · PythonThis repository provides a toolkit for analyzing the internal activations and properties of the Mamba-3 language model, including scripts for capturing activations, performing changepoint analysis, and probing GPU performance.61.5/100AdvancedRickMachine Learning
15EmblaV2Training Experiment · HTML60.8/100Advancedeze770Machine Learning
16kernel-workArchitecture Modification / Research · PythonThis repository implements a gather-matmul-scatter overlay for the `deep_chaos_scheduler` to optimize training by computing only on active channels. It includes the overlay implementation, tests for correctness, and benchmarks to measure performance impact.60.5/100AdvancedRickMachine Learning
174cast-livive-netEducational Implementation · RustThis repository implements four machine learning classifiers (centroid, k-NN, perceptron, and MLP) from scratch in Rust, with a fixed input/output contract for comparison. It includes educational tooling for data preparation, model training, evaluation, and visualization in a…60.3/100AdvancedJarad PeckenpaughMachine Learning

What it is

Where it counts

Around it on the Machine Learning board

More from eze770