ChunJyeBehBeh
ChunJyeBehBeh
Hello, may I know how to run the recognition_model with RGB camera? Which code file to run and where should I put the pretrained model?
Hello, may I know have you solved the problem?
@HighGuard Hello, have you manage to solve it at the end?
@SamDecrock Hello, at the end have you successfully crack the card?
Hello, @songxd66 @ryanlewist @te36051 @iamycee Have y'all train the ddqn model successfully? My model stuck below 50 steps....  Ignore the left image.... right side is the total reward per...
@cxhmikegithub You can try what I have said in the comment above. Change the param file.
Hello, did yall solve the problem?
The policy that I used is DDPG and SAC. I have updated on the issue above. Thanks for your reply~
Yes I am using the default hyperparameters.... May I know which part should I change in order to using raw image to train a SAC model? In the sac.yml, change...
Hello, I change the policy to `CnnPolicy` and increase the layer to `policy_kwargs: “dict(layers=[64,64,64,64])”`. However, I still didn't manage to train the agent with raw image input... Any other parameters...