Accessing weights of neural network of a policy

How severe does this issue affect your experience of using Ray?

  • Medium: It contributes to significant difficulty to complete my task, but I can work around it.

I have a PPO algorithm with multiple policies. I’d like to see the weights of the neural network of one of my policies, i.e. access the actual numbers for these weights. How can I do that?

I got as far as algorithm.workers.local_worker().policy_map['policy_0'].model but couldn’t find the weights there.


I got my answer on Stack Overflow: python - Get the neural network weights out of a Tensorflow `Graph` - Stack Overflow

1 Like