OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

Rl Plotter

Rl Plotter is a Python library that logs reinforcement-learning evaluation results and plots learning curves from experiment logs.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Rl Plotter — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Rl Plotter when evaluation code or supported experiment logs provide data you want to inspect as learning curves, especially when comparing multiple runs or metrics.

Who it is for

  • Reinforcement-learning developers who want to visualize evaluation scores during or after training.
  • Researchers comparing logged runs or tracking additional experiment variables.

Documented uses

  • Record evaluation scores against training steps.
  • Plot curves from one or multiple experiment logs.
  • Filter experiments, average grouped curves and display shaded variation.
  • Track additional variables and select CSV fields for plot axes.
Before you choose

Requirements & limits

  • The README recommends adding Rl Plotter's logger to evaluation code and also describes support for OpenAI Spinning Up logs.
  • OpenAI Baselines bench.Monitor is mentioned as a supported option, but the README labels it not recommended.
  • The tool provides native Matplotlib and a separate Spinning Up-style plotting command.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Log and plot evaluation learning curves

Record evaluation scores against training steps and create a plot from the resulting logs.

Before you start

  • Python environment with rl_plotter installed using pip or from source.
  • Evaluation code that can provide scores and current training steps.

Steps

  1. Install with the command below, or use the repository's source-install instruction.

    Documented command
    pip install rl_plotter

  2. Import Logger from rl_plotter.logger and initialize it in evaluation code with experiment name, environment name, seed and locals.

  3. Call logger.update(score=evaluation_score_list, total_steps=current_training_steps) to record evaluation results.

  4. From the log directory, run rl_plotter --save --show to display and save a plot.

Expected outcome

A saved and displayed learning-curve plot based on the logged evaluation results.

Guide limitations

  • The guide covers the README's basic logger and plotting workflow; it does not specify a complete training program.
  • Plotting from multiple logs requires running the command from their parent directory.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
gxywy/rl-plotter · Official homepage title · retained in its source language
How we review sourcesSuggest a correction