Struct LearningConfig 

pub struct LearningConfig {

    pub alpha: f64,
    pub gamma: f64,
    pub epsilon: f64,
    pub epsilon_decay: f64,
    pub epsilon_min: f64,
    pub distill_top_k: usize,
    pub distill_threshold: f64,
    pub elastic_lambda: f64,
    pub elastic_pin_count: usize,
    pub federated_blend: f64,
    pub meta_top_k: usize,
    pub pmi_min_count: usize,
    pub active_modes: HashSet<LearningMode>,
}

Full HELM hyperparameter configuration.

Examples

use lmm_agent::cognition::learning::config::LearningConfig;

let cfg = LearningConfig::builder()
    .alpha(0.05)
    .gamma(0.95)
    .epsilon(0.2)
    .build();

assert_eq!(cfg.alpha, 0.05);

Fields

alpha: f64

Temporal-difference learning rate α ∈ (0, 1].

gamma: f64

Discount factor γ ∈ [0, 1].

epsilon: f64

Initial ε-greedy exploration probability ∈ (0, 1].

epsilon_decay: f64

Per-episode ε decay multiplier ∈ (0, 1].

epsilon_min: f64

Minimum exploration probability floor.

distill_top_k: usize

Number of top cold entries promoted to the knowledge index per distillation.

distill_threshold: f64

Minimum reward score required for a cold entry to be distillation-eligible.

elastic_lambda: f64

Elastic penalty strength λ.

elastic_pin_count: usize

Number of recall activations before an entry is considered “pinned.”

federated_blend: f64

Blend weight for federated merge: 1.0 = keep local only, 0.0 = remote only.

meta_top_k: usize

Number of task prototypes considered when computing meta-adaptation offsets.

pmi_min_count: usize

Minimum token-pair co-occurrence count required before PMI is computed.

active_modes: HashSet<LearningMode>

Set of learning modes that are active.

Implementations

impl LearningConfig

pub fn builder() -> LearningConfigBuilder

Returns a LearningConfigBuilder for ergonomic construction.

pub fn is_mode_active(&self, mode: LearningMode) -> bool

Returns true when the given mode is active.

Examples

use lmm_agent::cognition::learning::config::LearningConfig;
use lmm_agent::types::LearningMode;

let cfg = LearningConfig::default();
assert!(cfg.is_mode_active(LearningMode::QTable));

Trait Implementations

impl Clone for LearningConfig

fn clone(&self) -> LearningConfig

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for LearningConfig

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for LearningConfig

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for LearningConfig

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for LearningConfig

fn eq(&self, other: &LearningConfig) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for LearningConfig

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for LearningConfig