Add additional hyperparameters to the RL Agent

[asaficontact]

We need to add the following additional hyperparameter options:

• Structure of Policy and Value network
• entropy coefficient for exploration

[Sujeeth13]

policy_kwargs = dict(
    activation_fn=torch.nn.ReLU,net_arch=dict(pi=[512,128,64,32,16], vf=[512,128,64,32,16])
    )

in model.config make a new policy_kwargs argument and pass this dict

[asaficontact]

check if entropy coefficient starts at a high point and reduces over the training i.e. exploration reducing over time as model is trained.