ML-Explorer is a project for monitoring ML-Agents training sessions and their outputs. ML-Agents is a powerful framework for creating intelligent agents in games and simulations using reinforcement learning, imitation learning, and other methods. ML-Explorer allows you to explore various models and their respective running training jobs (headless server instances) and visualize their progress and performance.
- Track and compare multiple ML-Agents training sessions and their outputs
- Generate reports and summaries of your ML-Agents results
- Analyze and visualize your ML-Agents data and metrics
- Optimize and improve your ML-Agents policies and parameters
- Experiment with different ML-Agents settings and scenarios
To use ML-Explorer, you need to have the following installed:
- [Microsoft Edge] browser
- [Unity Hub] and [Unity Editor] with ML-Agents package
- [Python] and [mlagents] package
To install ML-Explorer, you can clone this repository or download the zip file. Then, open the ML-Explorer folder in your preferred code editor.
To use ML-Explorer, you need to follow these steps:
- Launch the Microsoft Edge browser and open the ML-Explorer web page.
- Launch the Unity Hub and open the ML-Agents project that you want to monitor.
- Launch the Python terminal and run the mlagents-learn command with the appropriate configuration file and environment name.
- On the ML-Explorer web page, enter the name of your training session and the port number that you are using for communication between Unity and Python.
- Click on the "Start Monitoring" button and watch the graphs and charts update in real time as your ML-Agents train.
- Repeat steps 2 to 5 for any other ML-Agents projects that you want to monitor simultaneously.
- To stop monitoring, click on the "Stop Monitoring" button and close the Unity and Python terminals.
ML-Explorer is licensed under the [MIT License].