[![enter image description here][1]][1] could anyone who can help me if we decompose them and combine back them into a single Q, what the network can learn? from my perspective，the V means the total reward when the agent follow the current policy;the Q means if we give a specific action then follow the current policy what the total reward;and if we get the optimal policy，the V will equal to Q;so we should learn to make the A reach zero;just like the answer ：https://datascience.stackexchange.com/questions/34074/dueling-dqn-cant-understand-its-mechanism

but in that paper，i cannot understand what is the matter if we cannot identify the sense that given Q we cannot recover V and A uniqueluy. Dueling DQN - can't understand its mechanism and it will get this blow finally： Dueling DQN - can't understand its mechanism

and as well as this： Dueling DQN - can't understand its mechanism

refer to this blog:https://medium.com/@awjuliani/simple-reinforcement-learning-with-tensorflow-part-4-deep-q-networks-and-beyond-8438a3e2b8df [1]: https://i.sstatic.net/1nwPj.png

could anyone who can help me if we decompose them and combine back them into a single Q, what the network can learn? from my perspective，the V means the total reward when the agent follow the current policy;the Q means if we give a specific action then follow the current policy what the total reward; and if we get the optimal policy，the V will equal to Q;so we should learn to make the A reach zero;just like the answer ：https://datascience.stackexchange.com/questions/34074/dueling-dqn-cant-understand-its-mechanism

but in that paper，i cannot understand what is the matter if we cannot identify the sense that given Q we cannot recover V and A uniqueluy.

and it will get this blow finally：

and as well as this：

refer to this blog:https://medium.com/@awjuliani/simple-reinforcement-learning-with-tensorflow-part-4-deep-q-networks-and-beyond-8438a3e2b8df

could anyone who can help me if we decompose them and combine back them into a single Q, what the network can learn?

[![enter image description here][1]][1] could anyone who can help me if we decompose them and combine back them into a single Q, what the network can learn? from my perspective，the V means the total reward when the agent follow the current policy;the Q means if we give a specific action then follow the current policy what the total reward;and if we get the optimal policy，the V will equal to Q;so we should learn to make the A reach zero;just like the answer ：https://datascience.stackexchange.com/questions/34074/dueling-dqn-cant-understand-its-mechanism

but in that paper，i cannot understand what is the matter if we cannot identify the sense that given Q we cannot recover V and A uniqueluy. Dueling DQN - can't understand its mechanism and it will get this blow finally： Dueling DQN - can't understand its mechanism

and as well as this： Dueling DQN - can't understand its mechanism

refer to this blog:https://medium.com/@awjuliani/simple-reinforcement-learning-with-tensorflow-part-4-deep-q-networks-and-beyond-8438a3e2b8df [1]: https://i.sstatic.net/1nwPj.png