henri/trictrac
1
1
Fork 0
Code Issues 14 Pull requests Actions Packages Projects 1 Releases Wiki Activity

doc params train bot

Browse source
This commit is contained in:
Henri Bourcereau 2025-08-10 17:45:53 +02:00
parent 778ac1817b
commit 1fb04209f5
1 changed files with 8 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

16
bot/src/dqn/burnrl/main.rs
View file

@ -14,16 +14,16 @@ fn main() {
// See also MEMORY_SIZE in dqn_model.rs : 8192
let conf = dqn_model::DqnConfig {
num_episodes: 40,
min_steps: 250.0, // min steps by episode (mise à jour par la fonction)
max_steps: 2000, // max steps by episode
dense_size: 256, // neural network complexity
eps_start: 0.9, // epsilon initial value (0.9 => more exploration)
eps_end: 0.05,
num_episodes: 40, // default : 40
min_steps: 250.0, // min of max steps by episode (mise à jour par la fonction)(default 1000 ?)
max_steps: 3000, // max steps by episode (default 1000 ?)
dense_size: 256, // neural network complexity (default 128)
eps_start: 0.9, // epsilon initial value (0.9 => more exploration) (default 0.9)
eps_end: 0.05, // (default 0.05)
// eps_decay higher = epsilon decrease slower
// used in : epsilon = eps_end + (eps_start - eps_end) * e^(-step / eps_decay);
// epsilon is updated at the start of each episode
eps_decay: 3000.0,
eps_decay: 5000.0, // default 1000 ?
gamma: 0.999, // discount factor. Plus élevé = encourage stratégies à long terme
tau: 0.005, // soft update rate. Taux de mise à jour du réseau cible. Plus bas = adaptation
@ -31,7 +31,7 @@ fn main() {
learning_rate: 0.001, // taille du pas. Bas : plus lent, haut : risque de ne jamais
// converger
batch_size: 32, // nombre d'expériences passées sur lesquelles pour calcul de l'erreur moy.
clip_grad: 100.0, // plafonnement du gradient : limite max de correction à apporter
clip_grad: 50.0, // limite max de correction à apporter au gradient (default 100)
};
println!("{conf}----------");
let agent = dqn_model::run::<Env, Backend>(&conf, false); //true);