Critic¶

`python_motion_planning.local_planner.ddpg.Critic` ¶

Bases: Module

Critic network to estimate the value function q(s,a).

Parameters:

Name	Type	Description	Default
`state_dim`	`int`	state dimension	required
`action_dim`	`int`	action dimension	required
`hidden_depth`	`int`	the number of hidden layers of the neural network	required
`hidden_width`	`int`	the number of neurons in hidden layers of the neural network	required
`min_state`	`Tensor`	minimum of each value in the state	required
`max_state`	`Tensor`	maximum of each value in the state	required
`min_action`	`Tensor`	minimum of each value in the action	required
`max_action`	`Tensor`	maximum of each value in the action	required

Calculate the Q-value of (s,a)

Parameters:

Name	Type	Description	Default
`s`	`Tensor`	state	required
`a`	`Tensor`	action	required

Returns:

Name	Type	Description
`q`	`Tensor`	Q-value of (s,a)