This feature is only available in AnyLogic 8.7.4+. If you are unable to export to Pathmind using this feature, please export as a standalone JAR instead or contact Pathmind support.
Once you finish configuring the Pathmind Helper, you must export your AnyLogic simulation to Pathmind to train a policy.
Step 1: Create a new RLExperiment in AnyLogic
Step 2: Update your RLExperiment settings to match your Simulation settings
You will only need to update Model Time and Randomness to match what you have set in your Simulation experiment.
If Model Time and Randomness do not match what you have set in your Simulation experiment, your reinforcement learning policy will be invalid!
Step 3: Open RLExperiment and click "Export to Pathmind"
Ignore the other RL Experiment properties. Only Model Time and Randomness must be configured. All other fields are handled by Pathmind Helper and will be ignored.
Step 4: Obtain your Pathmind API Key
Go to the Account Page here: https://app.pathmind.com/account.
From there, copy your API Key.
Step 5: Back in AnyLogic, paste in your API Key
Click Next and wait for your AnyLogic model to upload. This can take up to 10 minutes depending on your internet speed and the size of your AnyLogic model.
Once the upload is complete, you will be presented with a link to your Pathmind experiment. This link will automatically open in your browser.