Networks

class A2CNetwork(input_shape, output_shape, n_features, **kwargs)

Bases: Module

__init__(input_shape, output_shape, n_features, **kwargs)

Initializes internal Module state, shared by both nn.Module and ScriptModule.

forward(state, **kwargs)

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class DDPGCriticNetwork(input_shape, output_shape, n_features, **kwargs)

Bases: Module

__init__(input_shape, output_shape, n_features, **kwargs)

Initializes internal Module state, shared by both nn.Module and ScriptModule.

forward(state, action)

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class DDPGActorNetwork(input_shape, output_shape, **kwargs)

Bases: Module

__init__(input_shape, output_shape, **kwargs)

Initializes internal Module state, shared by both nn.Module and ScriptModule.

forward(state)

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class SACCriticNetwork(input_shape, output_shape, n_features, **kwargs)

Bases: Module

__init__(input_shape, output_shape, n_features, **kwargs)

Initializes internal Module state, shared by both nn.Module and ScriptModule.

forward(state, action)

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class SACActorNetwork(input_shape, output_shape, n_features, **kwargs)

Bases: Module

__init__(input_shape, output_shape, n_features, **kwargs)

Initializes internal Module state, shared by both nn.Module and ScriptModule.

forward(state)

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class TD3CriticNetwork(input_shape, output_shape, n_features, **kwargs)

Bases: Module

__init__(input_shape, output_shape, n_features, **kwargs)

Initializes internal Module state, shared by both nn.Module and ScriptModule.

forward(state, action)

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class TD3ActorNetwork(input_shape, output_shape, n_features, **kwargs)

Bases: Module

__init__(input_shape, output_shape, n_features, **kwargs)

Initializes internal Module state, shared by both nn.Module and ScriptModule.

forward(state)

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class TRPONetwork(input_shape, output_shape, n_features, **kwargs)

Bases: Module

__init__(input_shape, output_shape, n_features, **kwargs)

Initializes internal Module state, shared by both nn.Module and ScriptModule.

forward(state, **kwargs)

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.