Hi Henrick,

To tell the truth I don’t have much experience in the continuous control domain myself. What you described is essentially how it is done however. This is an excerpt from the A3C paper describing how to augment the network for continuous control:

“The most important difference in the architecture is in the the output layer of the policy network. Unlike the discrete action domain where the action output is a Softmax, here the two outputs of the policy network are two real number vectors which we treat as the mean vector µ and scalar variance σ2 of a multidimensional normal distribution with a spherical covariance. To act, the input is passed through the model to the output layer where we sample from the normal distribution determined by µ and σ2. In practice, µ is modeled by a linear layer and σ2 by a SoftPlus operation, log(1 + exp(x)), as the activation computed as a function of the output of a linear layer. In our experiments with continuous control problems the networks for policy network and value network do not share any parameters, though this detail is unlikely to be crucial. Finally, since the episodes were typically at most several hundred time steps long, we did not use any bootstrapping in the policy or value function updates and batched each episode into a single update.”

Hope that is helpful!