task_l0_sensors (faber_neuroevolution v1.2.4)

View Source

Task Silo L0 Sensors - Collects and normalizes sensor inputs for TWEANN.

Part of the Liquid Conglomerate v2 architecture. This module collects evolution statistics and transforms them into normalized inputs for the L0 hyperparameter-tuning TWEANN.

Responsibilities

1. Collect evolution statistics from neuroevolution_server 2. Compute derived metrics (velocities, trends) 3. Normalize all values to appropriate ranges for TWEANN input 4. Handle cross-silo input signals 5. Maintain state for velocity and trend calculations

Usage

%% Start the sensor collector {ok, Pid} = task_l0_sensors:start_link(Config),

%% Update with new evolution stats (called by neuroevolution_server) task_l0_sensors:update_stats(Pid, Stats),

%% Get current sensor vector (ordered list) SensorVector = task_l0_sensors:get_sensor_vector(Pid), %% Returns: [0.82, 0.65, 0.12, ...] (16 values)

Summary

Functions

get_sensor_vector()

Get ordered sensor vector for TWEANN input.

get_sensor_vector(Pid)

Get ordered sensor vector from specific server.

get_sensors()

Get named sensor map.

get_sensors(Pid)

Get named sensor map from specific server.

handle_call(Request, From, State)
handle_cast(Msg, State)
handle_info(Info, State)
init(Config)
set_realm(Realm)

Set the realm for event publishing.

start_link()

Start the sensor collector with default configuration.

start_link(Config)

Start the sensor collector with custom configuration.

terminate(Reason, State)
update_archive_stats(Stats)

Update archive statistics.

update_cross_silo_signal(SignalName, Value)

Update cross-silo signal from another silo.

update_crossover_success(Success)

Record a crossover outcome (success or failure).

update_mutation_impact(FitnessChange)

Record a mutation impact (fitness change).

update_stats(Stats)

Update with new evolution statistics.

update_stats(Pid, Stats)

Update with new evolution statistics (specific server).

Functions

get_sensor_vector()

-spec get_sensor_vector() -> [float()].

Get ordered sensor vector for TWEANN input.

Returns a list of 21 float values in the order defined by task_l0_morphology:sensor_names/0.

get_sensor_vector(Pid)

-spec get_sensor_vector(pid()) -> [float()].

Get ordered sensor vector from specific server.

get_sensors()

-spec get_sensors() -> map().

Get named sensor map.

get_sensors(Pid)

-spec get_sensors(pid()) -> map().

Get named sensor map from specific server.

handle_call(Request, From, State)

handle_cast(Msg, State)

handle_info(Info, State)

init(Config)

set_realm(Realm)

-spec set_realm(binary()) -> ok.

Set the realm for event publishing.

Use this to dynamically update the realm when a training session starts. Events will be published to the topic for the specified realm.

start_link()

-spec start_link() -> {ok, pid()} | ignore | {error, term()}.

Start the sensor collector with default configuration.

start_link(Config)

-spec start_link(map()) -> {ok, pid()} | ignore | {error, term()}.

Start the sensor collector with custom configuration.

terminate(Reason, State)

update_archive_stats(Stats)

-spec update_archive_stats(map()) -> ok.

Update archive statistics.

Expected keys in Stats map: - size: current archive size - max_size: maximum archive size - avg_fitness: average fitness in archive - fitness_variance: fitness variance in archive - avg_generation: average generation of entries (for staleness)

update_cross_silo_signal(SignalName, Value)

-spec update_cross_silo_signal(atom(), float()) -> ok.

Update cross-silo signal from another silo.

update_crossover_success(Success)

-spec update_crossover_success(boolean()) -> ok.

Record a crossover outcome (success or failure).

update_mutation_impact(FitnessChange)

-spec update_mutation_impact(float()) -> ok.

Record a mutation impact (fitness change).

update_stats(Stats)

-spec update_stats(map()) -> ok.

Update with new evolution statistics.

update_stats(Pid, Stats)

-spec update_stats(pid(), map()) -> ok.

Update with new evolution statistics (specific server).