src.gridmind.policies.parameterized.actor_critic_policy

Classes

ActorCriticPolicy

Helper class that provides a standard way to create an ABC using

Functions

layer_init(layer[, std, bias_const])

Module Contents

src.gridmind.policies.parameterized.actor_critic_policy.layer_init(layer, std=np.sqrt(2), bias_const=0.0)

class src.gridmind.policies.parameterized.actor_critic_policy.ActorCriticPolicy(observation_shape, num_actions)

Bases: gridmind.policies.parameterized.base_parameterized_policy.BaseParameterizedPolicy

Helper class that provides a standard way to create an ABC using inheritance.

construct_actor_critic_networks()

get_value(x)

get_action_and_value(x, action=None)

get_action(state)

get_action_prob(state, action)

abstract update(state, action)