nip.scenario_base.agents.CombinedValueHead#

class nip.scenario_base.agents.CombinedValueHead(*args, **kwargs)[source]#

A module which combines all the agent value heads together.

Parameters:

hyper_params (HyperParameters) – The parameters of the experiment.
settings (ExperimentSettings) – The settings of the experiment.
protocol_handler (ProtocolHandler) – The protocol handler for the experiment.
value_heads (dict[str, AgentValueHead]) – The agent value heads to combine.

Methods Summary

`__init__`(hyper_params, settings, ...)	Initialize internal Module state, shared by both nn.Module and ScriptModule.
`_restrict_input_to_visible_channels`(...)	Restrict an agent's input to its visible message channels.
`forward`(data)	Forward pass through the combined value head.

Attributes

`T_destination`
`additional_in_keys`
`additional_out_keys`
`call_super_init`
`device`	The device used by the agent part.
`dump_patches`
`excluded_in_keys`
`excluded_out_keys`
`in_keys`	The keys required by the module.
`out_keys`	The keys produced by the module.
`out_keys_source`
`training`

Methods

__init__(hyper_params: HyperParameters, settings: ExperimentSettings, protocol_handler: ProtocolHandler, value_heads: dict[str, AgentValueHead])[source]#: Initialize internal Module state, shared by both nn.Module and ScriptModule.

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

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.

Forward pass through the combined value head.

Parameters:: data (TensorDict) – The input to the combined value head.
Returns:: value_output (TensorDict) – The output of the combined value head.

nip.scenario_base.agents.CombinedValueHead