Load policy's networks from a saved model.

Decay the actor and critic learning rates. :param episode: (int) current training episode. :param episodes: (int) total numbe

Yield training data for non-chunked RNN training. :param advantages: (np.ndarray) advantage estimates. :param num_mini_batch:

Update actor and critic networks. :param sample: (Tuple) contains data batch with which to update networks. :update_actor: (b

Yield training data for chunked RNN training. :param advantages: (np.ndarray) advantage estimates. :param num_mini_batch: (in

Tell all the environments to start taking a step with the given actions. Call step_wait() to get the results of the step.

Wait for the step taken with step_async(). Returns (obs, rews, dones, infos): - obs: an array of observations, or a dict of

Mode 0: disconnect all UEs and refuse new connections Mode 1: refuse new connections Mode 2: accept new connections M

Measure SINR over the grid.

Perform a training update using minibatch GD. :param buffer: (SharedReplayBuffer) buffer containing training data. :param upd