std1.0.0-beta-7 SafeC docs

std :: ml::rl

Struct std::PgConfig

#include <std/ml/rl.h> source

struct PgConfig {
    int algo;
    unsigned long hidden;
    unsigned long hiddenLayers;
    int act;
    float gamma;
    float gaeLambda;
    float lr;
    float entropyCoef;
    float valueCoef;
    float clipEps;
    unsigned long epochs;
    unsigned long minibatch;
    float clipNorm;
    int normalizeAdv;
    unsigned long seed;
}

Fields

§int algosource

PG_*

§unsigned long hiddensource
§unsigned long hiddenLayerssource
§int actsource
§float gammasource
§float gaeLambdasource

A2C / PPO advantages (1 = Monte Carlo, 0 = one-step TD)

§float lrsource
§float entropyCoefsource
§float valueCoefsource
§float clipEpssource

PPO ratio clip

§unsigned long epochssource

PPO passes over a rollout

§unsigned long minibatchsource

PPO minibatch size

§float clipNormsource

0 = off

§int normalizeAdvsource
§unsigned long seedsource

Methods

§static struct PgConfig default(int algo)source · definition

2 hidden layers of 64 (tanh), gamma 0.99, lambda 0.95, Adam lr 1e-3 (3e-3 for REINFORCE), entropy 0.01, value 0.5, clip 0.2, 4 epochs of 64, grad clip 0.5, normalized advantages.