src.gridmind.policies.parameterized.discrete_action_mlp_policy

Classes

DiscreteActionMLPPolicy

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

Module Contents

class src.gridmind.policies.parameterized.discrete_action_mlp_policy.DiscreteActionMLPPolicy(observation_shape: tuple, num_actions: int, num_hidden_layers: int = 0, in_features: int = 16, out_features: int = 16, use_bias: bool = True)

Bases: gridmind.policies.parameterized.base_parameterized_policy.BaseParameterizedPolicy

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

num_hidden_layers = 0

in_features = 16

out_features = 16

hidden_layers

_create_hidden_layer(use_bias: bool)

forward(x)

get_action(state)

get_actions(states)

get_action_prob(state, action)

get_all_action_probabilities(states)

update(state, action, value)