Maybe I'm pointing out the obvious, but there are references to Q* in the docs[1]. Specifically it's just the Bellman equation describing the optimal action-value function.
It would be kind of weird if OpenAI invented their own thing called Q* which collides with an existing name in a topic I'd expect them to be familiar with.
5 comments
[ 4.3 ms ] story [ 26.6 ms ] threadIt would be kind of weird if OpenAI invented their own thing called Q* which collides with an existing name in a topic I'd expect them to be familiar with.
https://spinningup.openai.com/en/latest/algorithms/ddpg.html