SAC

class SAC(model, gamma=None, tau=None, alpha=None, actor_lr=None, critic_lr=None)

基类：Algorithm

__init__(model, gamma=None, tau=None, alpha=None, actor_lr=None, critic_lr=None)

SAC algorithm

参数:

• model (parl.Model) – forward network of actor and critic.

• gamma (float) – discounted factor for reward computation

• tau (float) – decay coefficient when updating the weights of self.target_model with self.model

• alpha (float) – temperature parameter determines the relative importance of the entropy against the reward

• actor_lr (float) – learning rate of the actor model

• critic_lr (float) – learning rate of the critic model

learn(obs, action, reward, next_obs, terminal)

Define the loss function and create an optimizer to minize the loss.

predict(obs)

Refine the predicting process, e.g,. use the policy model to predict actions.

sample(obs)

Define the sampling process. This function returns an action with noise to perform exploration.