3

I am trying to implement a simple case of deep Q learning in R, using the neuralnet package.

I have an initial network with initial random weights. I use it to generate some experience for my agent and as a result, I get states and targets. Then I fit the states to the target and get a new network with new weights.

How do I have to combine the new weights and the initial weights? Do I simply keep the new weights and discard the initial weights?

vonjd
  • 4,202
  • 3
  • 44
  • 68
Andreas
  • 31
  • 1
  • It would be helpful if you could share the code so that one can see what you are trying to achieve and where the problem lies. Is there some source on which you build your concrete example? – vonjd Mar 09 '21 at 17:23
  • Perhaps this post might help to understand the basic reinforcement algorithm: https://blog.ephorie.de/reinforcement-learning-life-is-a-maze – vonjd Mar 09 '21 at 17:44

0 Answers0