IBM / federated-learning-lib

A library for federated learning (a distributed machine learning process) in an enterprise environment.
Other
500 stars 136 forks source link

Dropping out agents while training on rl examples #134

Open CriZ-sd opened 1 year ago

CriZ-sd commented 1 year ago

Hello,

i noticed that while training in rl examples, some of the agents are dropped out. I have also two images one from a custom example (with three agents) and one from the cartpole env example that is included in the ibmfl examples (with five agents).

rewards

rewards_2

As it is depicted in both cases, the agents are gradually dropped out and finally, only one agent remains at the training processes. Is this the expected behavior ? Any idea why this happens?