lloydy8

@lloydy8·2 public vizzes

Untitled

This interactive visualization shows how a deep reinforcement learning agent’s performance evolves over training timesteps, with multiple score series tracking different agents or runs. The chart animates through the training timeline, allowing viewers to compare score trajectories and observe how performance improves over time. Built with D3.js v7, the SVG-based visualization uses a slider to scrub through timesteps and dynamically update the line chart. The data comes from a hardcoded score list, and the page includes tabbed navigation and buttons to switch between overview and detailed views of the training process.

Sep 6, 2022

Loading thumbnail…

Fork of Fork of Stylized Line Chart

This visualization shows the relationship between training steps and reward values across multiple data series, with each point annotated by its pollutant label. A natural cubic spline connects the data points, with circular markers emphasizing individual observations. The chart is built using React and D3 v5, employing `scaleTime` for the x-axis, `scaleLinear` for the y-axis, and the `line` generator with `curveNatural` for the smoothed path. Data is loaded asynchronously from an external CSV file via `d3.csv`, and the SVG output is styled with a Poppins font and custom tick colors.

Jul 30, 2022