nip.scenario_base.agents.RandomAgentPolicyHead#

class nip.scenario_base.agents.RandomAgentPolicyHead(hyper_params: HyperParameters, settings: ExperimentSettings, agent_name: str, protocol_handler: ProtocolHandler)[source]#

A policy head which samples actions randomly.

Methods Summary

`__init__`(hyper_params, settings, agent_name, ...)
`forward`(data)	Forward pass through the agent part.
`get_state_dict`()	Get the state of the agent part as a dict.
`set_state`(checkpoint)	Set the state of the agent from a checkpoint.

Attributes

`agent_id`	The ID of the agent.
`agent_level_in_keys`
`agent_level_out_keys`
`env_level_in_keys`
`env_level_out_keys`
`has_decider`	Whether the policy head has an output yielding a decision.
`in_keys`	The keys required by the module.
`is_prover`	Whether the agent is a prover.
`is_verifier`	Whether the agent is a verifier.
`max_message_rounds`	The maximum number of message rounds in the protocol.
`num_visible_message_channels`	The number of message channels visible to the agent.
`out_keys`	The keys produced by the module.
`required_pretrained_models`	The pretrained models used by the agent.
`visible_message_channel_indices`	The indices of the message channels visible to the agent.
`visible_message_channel_mask`	The mask for the message channels visible to the agent.
`visible_message_channel_names`	The names of the message channels visible to the agent.

Methods

__init__(hyper_params: HyperParameters, settings: ExperimentSettings, agent_name: str, protocol_handler: ProtocolHandler)[source]#

abstract forward(data: Any) → Any[source]#

Forward pass through the agent part.

get_state_dict() → dict[source]#

Get the state of the agent part as a dict.

This method should be implemented by subclasses capable of saving their state.

set_state(checkpoint: AgentState)[source]#

Set the state of the agent from a checkpoint.

This method should be overridden by subclasses to restore the state of the agent from a checkpoint.

Parameters:: checkpoint (AgentCheckpoint) – The checkpoint to restore the state from.

nip.scenario_base.agents.RandomAgentPolicyHead