nip.scenario_base.agents.PureTextCombinedWhole

class nip.scenario_base.agents.PureTextCombinedWhole(hyper_params: HyperParameters, settings: ExperimentSettings, protocol_handler: ProtocolHandler, wholes: dict[str, WholeAgent])

Base class for modules which combine whole pure-text agents together.

Methods Summary

__init__(hyper_params, settings, ...)
_restrict_input_to_visible_channels(...)	Restrict an agent's input to its visible message channels.
forward(data, environment)	Run a forward pass through all the agents and combine the output.

Attributes

additional_in_keys
additional_out_keys
excluded_in_keys
excluded_out_keys
in_keys	The keys required by the module.
out_keys	The keys produced by the module.

Methods

__init__(hyper_params: HyperParameters, settings: ExperimentSettings, protocol_handler: ProtocolHandler, wholes: dict[str, WholeAgent])

_restrict_input_to_visible_channels(agent_name: str, input_array: Tensor | ndarray[Any, dtype[_ScalarType_co]], shape_spec: str) → Tensor

Restrict an agent’s input to its visible message channels.

Agents only receive messages from the channels they can see. This function restricts the input to the agent to only the visible message channels.

Parameters:

• agent_name (str) – The name of the agent.

• input_array (Tensor | NDArray) – The input array to the agent.

• shape_spec (str) – The shape of the input. This is a space-separated string of the dimensions of the input. One of these must be “channel”.

Returns:

restricted_input (Tensor | NDArray) – The input restricted to the visible message channels.

abstract forward(data: NestedArrayDict, environment: PureTextEnvironment) → NestedArrayDict

Run a forward pass through all the agents and combine the output.