resource_l0_morphology (faber_neuroevolution v1.2.4)

Resource Silo L0 Morphology - TWEANN sensor/actuator definitions.

Part of the Liquid Conglomerate v2 architecture. Defines the neural network morphology for the Resource Silo's L0 reactive controller.

Architecture

L0 is a TWEANN (Topology and Weight Evolving Artificial Neural Network) that: - Takes 15 sensor inputs (13 resource + 2 self-play archive) - Produces 10 actuator outputs (8 resource + 1 archive control + 1 timeout control) - Has 8 hyperparameters that L1 can tune - Has 5 L1 hyperparameters that L2 can tune

Time Constant

tau_L0 = 5 seconds (fast adaptation for resource management)

Summary

Functions

actuator_count()

Number of actuators (neural network outputs).

actuator_names()

Ordered list of actuator names.

actuator_spec(_)

Get specification for an actuator.

get_l0_bounds()

Get bounds for L0 hyperparameters.

get_l0_defaults()

Get default values for L0 hyperparameters.

get_l1_bounds()

Get bounds for L1 hyperparameters.

get_l1_defaults()

Get default values for L1 hyperparameters.

l0_hyperparameter_spec(_)

Get specification for an L0 hyperparameter.

l0_hyperparameters()

List of L0 hyperparameter names.

l1_hyperparameter_spec(_)

Get specification for an L1 hyperparameter.

l1_hyperparameters()

List of L1 hyperparameter names.

sensor_count()

Number of sensors (neural network inputs).

sensor_names()

Ordered list of sensor names.

sensor_spec(_)

Get specification for a sensor.

tau_l0()

L0 time constant - 5 seconds for reactive resource control.

tau_l1()

L1 time constant - 30 seconds for tactical adaptation.

tau_l2()

L2 time constant - 5 minutes for strategic learning.

Functions

actuator_count()

-spec actuator_count() -> pos_integer().

Number of actuators (neural network outputs).

actuator_names()

-spec actuator_names() -> [atom()].

Ordered list of actuator names.

actuator_spec(_)

-spec actuator_spec(atom()) -> map() | undefined.

Get specification for an actuator.

Returns a map with: - name: Actuator name - range: {Min, Max} target range (for denormalization) - target: What system this affects - description: Human-readable description

get_l0_bounds()

-spec get_l0_bounds() -> map().

Get bounds for L0 hyperparameters.

get_l0_defaults()

-spec get_l0_defaults() -> map().

Get default values for L0 hyperparameters.

get_l1_bounds()

-spec get_l1_bounds() -> map().

Get bounds for L1 hyperparameters.

get_l1_defaults()

-spec get_l1_defaults() -> map().

Get default values for L1 hyperparameters.

l0_hyperparameter_spec(_)

-spec l0_hyperparameter_spec(atom()) -> map() | undefined.

Get specification for an L0 hyperparameter.

l0_hyperparameters()

-spec l0_hyperparameters() -> [atom()].

List of L0 hyperparameter names.

l1_hyperparameter_spec(_)

-spec l1_hyperparameter_spec(atom()) -> map() | undefined.

Get specification for an L1 hyperparameter.

l1_hyperparameters()

-spec l1_hyperparameters() -> [atom()].

List of L1 hyperparameter names.

Note: These are called "meta-parameters" from L1's perspective, but "hyperparameters" from L2's perspective.

sensor_count()

-spec sensor_count() -> pos_integer().

Number of sensors (neural network inputs).

sensor_names()

-spec sensor_names() -> [atom()].

Ordered list of sensor names.

sensor_spec(_)

-spec sensor_spec(atom()) -> map() | undefined.

Get specification for a sensor.

Returns a map with: - name: Sensor name - range: {Min, Max} normalized range - source: Where the data comes from - description: Human-readable description

tau_l0()

-spec tau_l0() -> pos_integer().

L0 time constant - 5 seconds for reactive resource control.

tau_l1()

-spec tau_l1() -> pos_integer().

L1 time constant - 30 seconds for tactical adaptation.

tau_l2()

-spec tau_l2() -> pos_integer().

L2 time constant - 5 minutes for strategic learning.