Skip to main content

Questions tagged [d3qn]

The tag has no usage guidance.

Filter by
Sorted by
Tagged with
1 vote
1 answer
195 views

Why do we need to have two heads in D3QN to obtain value and advantage separately, if V is the average of Q values?

I have two questions on the Dueling DQN paper. First, I have an issue on understanding the identifiability that Dueling DQN paper mentions: Here is my question: If we have given Q-values $Q(s, a; \...
Afshin Oroojlooy's user avatar
1 vote
2 answers
1k views

Questions on the identifiability issue and equations 8 and 9 in the D3QN paper

I have difficulty understanding the following paragraph in the below excerpts from page 4 to page 5 from the paper Dueling Network Architectures for Deep Reinforcement Learning. The author said "...
Cheng's user avatar
  • 85
1 vote
0 answers
71 views

How does having zero advantage help with identifiability?

I am reading the D3QN paper and they have the following paragraph - Equation (7) is unidentifiable in the sense that given $Q$ we cannot recover $V$ and $A$ uniquely. To see this, add a constant to $...
desert_ranger's user avatar