Whenever you are doing reinforcement learning you periodically update the target network based on the weights of the Q network. While I do understand this helps create a stable target I do not understand how it helps the Q networks accuracy. If I am updating the Q network much more frequently than I am the target network then wont the Q network converge to and estimate of the target network that is inaccurate since the target network is being updated much slower ?
2
-
$\begingroup$ I think this ai.stackexchange.com/a/13459/69468 already answers your question $\endgroup$– Luca AnzaloneJul 2 at 13:50
-
1$\begingroup$ oh wow perfect this is exactly what I needed $\endgroup$– StefJul 2 at 16:59
Add a comment
|