Reinforcement Learning Simulink Block Inital Policy
3 views (last 30 days)
Show older comments
Syed Muhammad Yousaf Hashmy
on 30 Jul 2019
Answered: Emmanouil Tzorakoleftherakis
on 2 Aug 2019
I want to give some initial policy to the reinforment learning block with DDPG agent. Not only the state and rewards but also the action needs to intialized how can it be done?
0 Comments
Answers (3)
Emmanouil Tzorakoleftherakis
on 1 Aug 2019
If you already have a policy with trained weights, you could just use that directly when creating the agent, instead of creating a new network from scratch. Is this what you were looking for?
0 Comments
Emmanouil Tzorakoleftherakis
on 2 Aug 2019
To use the rl agent block, you need to create an agent first, which also requires a policy architecture. When you set up your neural network, you can specify initial values for the weights using, e.g., the 'Weights' option of the fully connected layer (or any layer that has learnable parameters).
0 Comments
See Also
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!