Adversarial IRL on Re-routing

Classes and Functions

cyber_train_airl_ieee123.evaluate_policy(env, model)

Evaluating the learned policy by running experiments in the environment

Parameters

  • cpenv (Gym.Env) – The cyber RL environment

  • model (torch.nn.Module) – Trained policy network model

Returns

average episode length, average reward

Return type

float

cyber_train_airl_ieee123.train_and_evaluate(channel_bws, router_qlimits, policy_net_train_len, airl_train_len, exp_trajectory_len)

For different combination of channel bandwidths and router queue limits and expert demonstrations, train and test the policy and saves the results, reward and policy network.

Parameters

  • channel_bws (list) – List of the channel bandwidths value considered in the communication network

  • router_qlimits (list) – List of the router queue upper bound considered in the network

  • policy_net_train_len (int) – Samples considered for training the policy network fed in the generator network as initial policy

  • airl_train_len (int) – Samples considered for training AIRL network

  • exp_tajectory_len (int) – Number of expert demonstration samples to be considered

Returns

Nothing

Return type

None