garage.torch.algos.mtsac
¶
This modules creates a MTSAC model in PyTorch.

class
MTSAC
(policy, qf1, qf2, replay_buffer, env_spec, *, num_tasks, eval_env, gradient_steps_per_itr, max_episode_length_eval=None, fixed_alpha=None, target_entropy=None, initial_log_entropy=0.0, discount=0.99, buffer_batch_size=64, min_buffer_size=int(10000.0), target_update_tau=0.005, policy_lr=0.0003, qf_lr=0.0003, reward_scale=1.0, optimizer=torch.optim.Adam, steps_per_epoch=1, num_evaluation_episodes=5, use_deterministic_evaluation=True)¶ Bases:
garage.torch.algos.SAC
A MTSAC Model in Torch.
This MTSAC implementation uses is the same as SAC except for a small change called “disentangled alphas”. Alpha is the entropy coefficient that is used to control exploration of the agent/policy. Disentangling alphas refers to having a separate alpha coefficients for every task learned by the policy. The alphas are accessed by using a the onehot encoding of an id that is assigned to each task.
 Parameters
policy (garage.torch.policy.Policy) – Policy/Actor/Agent that is being optimized by SAC.
qf1 (garage.torch.q_function.ContinuousMLPQFunction) – QFunction/Critic used for actor/policy optimization. See Soft ActorCritic and Applications.
qf2 (garage.torch.q_function.ContinuousMLPQFunction) – QFunction/Critic used for actor/policy optimization. See Soft ActorCritic and Applications.
replay_buffer (ReplayBuffer) – Stores transitions that are previously collected by the sampler.
env_spec (EnvSpec) – The env_spec attribute of the environment that the agent is being trained in.
num_tasks (int) – The number of tasks being learned.
max_episode_length_eval (int or None) – Maximum length of episodes used for offpolicy evaluation. If None, defaults to max_episode_length.
eval_env (Environment) – The environment used for collecting evaluation episodes.
gradient_steps_per_itr (int) – Number of optimization steps that should occur before the training step is over and a new batch of transitions is collected by the sampler.
fixed_alpha (float) – The entropy/temperature to be used if temperature is not supposed to be learned.
target_entropy (float) – target entropy to be used during entropy/temperature optimization. If None, the default heuristic from Soft ActorCritic Algorithms and Applications is used.
initial_log_entropy (float) – initial entropy/temperature coefficient to be used if a fixed_alpha is not being used (fixed_alpha=None), and the entropy/temperature coefficient is being learned.
discount (float) – The discount factor to be used during sampling and critic/q_function optimization.
buffer_batch_size (int) – The number of transitions sampled from the replay buffer that are used during a single optimization step.
min_buffer_size (int) – The minimum number of transitions that need to be in the replay buffer before training can begin.
target_update_tau (float) – A coefficient that controls the rate at which the target q_functions update over optimization iterations.
policy_lr (float) – Learning rate for policy optimizers.
qf_lr (float) – Learning rate for q_function optimizers.
reward_scale (float) – Reward multiplier. Changing this hyperparameter changes the effect that the reward from a transition will have during optimization.
optimizer (torch.optim.Optimizer) – Optimizer to be used for policy/actor, q_functions/critics, and temperature/entropy optimizations.
steps_per_epoch (int) – Number of train_once calls per epoch.
num_evaluation_episodes (int) – The number of evaluation episodes used for computing eval stats at the end of every epoch.
use_deterministic_evaluation (bool) – True if the trained policy should be evaluated deterministically.

to
(self, device=None)¶ Put all the networks within the model on device.
 Parameters
device (str) – ID of GPU or CPU.

train
(self, trainer)¶ Obtain samplers and start actual training for each epoch.
 Parameters
trainer (Trainer) – Gives the algorithm the access to :method:`~Trainer.step_epochs()`, which provides services such as snapshotting and sampler control.
 Returns
The average return in last epoch cycle.
 Return type

train_once
(self, itr=None, paths=None)¶ Complete 1 training iteration of SAC.
 Parameters
 Returns
loss from actor/policy network after optimization. torch.Tensor: loss from 1st qfunction after optimization. torch.Tensor: loss from 2nd qfunction after optimization.
 Return type
torch.Tensor

optimize_policy
(self, samples_data)¶ Optimize the policy q_functions, and temperature coefficient.
 Parameters
samples_data (dict) – Transitions(S,A,R,S’) that are sampled from the replay buffer. It should have the keys ‘observation’, ‘action’, ‘reward’, ‘terminal’, and ‘next_observations’.
Note
samples_data’s entries should be torch.Tensor’s with the following shapes:
observation: \((N, O^*)\) action: \((N, A^*)\) reward: \((N, 1)\) terminal: \((N, 1)\) next_observation: \((N, O^*)\)
 Returns
loss from actor/policy network after optimization. torch.Tensor: loss from 1st qfunction after optimization. torch.Tensor: loss from 2nd qfunction after optimization.
 Return type
torch.Tensor