Skip to main content
🌍 Public

Share visualization

Send this visualization to others.

Agent Performance over Time in Walker

Public visualization

Agent Performance over Time in Walker

0 stars0🌍 Public
CChrisKort
Last edited Oct 28, 2019
Created on Oct 27, 2019

This example visualizes the performance of a VPG (Vanilla Policy Gradient) agent over time in the Walker environment, plotting average episode return against interaction count. The code uses D3 v5 APIs to create an SVG line chart with a basis-curved line path, styled axes with tick marks and labels, and a title. Data is loaded from a remote CSV and processed for numerical fields before rendering.

AI-generated description

Comments

Sign in to join the discussion.

MIT Licensed