High variance in performance of q-learning agents trained with same parameters

tux_tina

I am training an agent to play a simple game using double deep q learning. However, the variance in agent performance is very high, even for agents trained with same model parameters. For example, I can train agent A and agent B using the exact parameters and agent A beats B 800 to 200. I think I understand why this is happening, when training starts the model is initialized with different weights, and this leads the model to find different...

Originally asked by Akavall on Stack Exchange (ai) (CC BY-SA 4.0).

uphilltech

Good thread on this — worth a read before you pay anyone to build it.

Discussion: https://ai.stackexchange.com/questions/12279/high-variance-in-performance-of-q-learning-agents-trained-with-same-parameters.

Want it set up for you? UphillTech.