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

fix workflow

Browse source
This commit is contained in:
Henri Bourcereau 2025-06-08 21:20:04 +02:00
parent bae0632f82
commit 7507ea5d78
6 changed files with 186 additions and 306 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

20
bot/src/strategy/default.rs
View file

@ -36,18 +36,20 @@ impl BotStrategy for DefaultStrategy {
} }
fn calculate_points(&self) -> u8 { fn calculate_points(&self) -> u8 {
let dice_roll_count = self // let dice_roll_count = self
.get_game() // .get_game()
.players // .players
.get(&self.player_id) // .get(&self.player_id)
.unwrap() // .unwrap()
.dice_roll_count; // .dice_roll_count;
let points_rules = PointsRules::new(&Color::White, &self.game.board, self.game.dice); // let points_rules = PointsRules::new(&Color::White, &self.game.board, self.game.dice);
points_rules.get_points(dice_roll_count).0 // points_rules.get_points(dice_roll_count).0
self.game.dice_points.0
} }
fn calculate_adv_points(&self) -> u8 { fn calculate_adv_points(&self) -> u8 {
self.calculate_points() // self.calculate_points()
self.game.dice_points.1
} }
fn choose_go(&self) -> bool { fn choose_go(&self) -> bool {

61
bot/src/strategy/dqn.rs
View file

@ -2,7 +2,9 @@ use crate::{BotStrategy, CheckerMove, Color, GameState, PlayerId, PointsRules};
use std::path::Path; use std::path::Path;
use store::MoveRules; use store::MoveRules;
use super::dqn_common::{SimpleNeuralNetwork, TrictracAction, get_valid_actions, sample_valid_action}; use super::dqn_common::{
get_valid_actions, sample_valid_action, SimpleNeuralNetwork, TrictracAction,
};
/// Stratégie DQN pour le bot - ne fait que charger et utiliser un modèle pré-entraîné /// Stratégie DQN pour le bot - ne fait que charger et utiliser un modèle pré-entraîné
#[derive(Debug)] #[derive(Debug)]
@ -91,26 +93,11 @@ impl BotStrategy for DqnStrategy {
} }
fn calculate_points(&self) -> u8 { fn calculate_points(&self) -> u8 {
// Utiliser le DQN pour choisir le nombre de points à marquer self.game.dice_points.0
if let Some(action) = self.get_dqn_action() {
if let TrictracAction::Mark { points } = action {
return points;
}
}
// Fallback : utiliser la méthode standard
let dice_roll_count = self
.get_game()
.players
.get(&self.player_id)
.unwrap()
.dice_roll_count;
let points_rules = PointsRules::new(&self.color, &self.game.board, self.game.dice);
points_rules.get_points(dice_roll_count).0
} }
fn calculate_adv_points(&self) -> u8 { fn calculate_adv_points(&self) -> u8 {
self.calculate_points() self.game.dice_points.1
} }
fn choose_go(&self) -> bool { fn choose_go(&self) -> bool {
@ -126,9 +113,40 @@ impl BotStrategy for DqnStrategy {
fn choose_move(&self) -> (CheckerMove, CheckerMove) { fn choose_move(&self) -> (CheckerMove, CheckerMove) {
// Utiliser le DQN pour choisir le mouvement // Utiliser le DQN pour choisir le mouvement
if let Some(action) = self.get_dqn_action() { if let Some(action) = self.get_dqn_action() {
if let TrictracAction::Move { move1, move2 } = action { if let TrictracAction::Move {
let checker_move1 = CheckerMove::new(move1.0, move1.1).unwrap_or_default(); dice_order,
let checker_move2 = CheckerMove::new(move2.0, move2.1).unwrap_or_default(); from1,
from2,
} = action
{
let dicevals = self.game.dice.values;
let (mut dice1, mut dice2) = if dice_order {
(dicevals.0, dicevals.1)
} else {
(dicevals.1, dicevals.0)
};
if from1 == 0 {
// empty move
dice1 = 0;
}
let mut to1 = from1 + dice1 as usize;
if 24 < to1 {
// sortie
to1 = 0;
}
if from2 == 0 {
// empty move
dice2 = 0;
}
let mut to2 = from2 + dice2 as usize;
if 24 < to2 {
// sortie
to2 = 0;
}
let checker_move1 = CheckerMove::new(from1, to1).unwrap_or_default();
let checker_move2 = CheckerMove::new(from2, to2).unwrap_or_default();
let chosen_move = if self.color == Color::White { let chosen_move = if self.color == Color::White {
(checker_move1, checker_move2) (checker_move1, checker_move2)
@ -155,4 +173,3 @@ impl BotStrategy for DqnStrategy {
} }
} }
} }

317
bot/src/strategy/dqn_common.rs
View file

@ -1,133 +1,45 @@
use std::cmp::max;
use serde::{Deserialize, Serialize}; use serde::{Deserialize, Serialize};
use store::{CheckerMove, Dice, GameEvent, PlayerId};
/// Types d'actions possibles dans le jeu /// Types d'actions possibles dans le jeu
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq)] #[derive(Debug, Clone, Serialize, Deserialize, PartialEq)]
pub enum TrictracAction { pub enum TrictracAction {
/// Lancer les dés /// Lancer les dés
Roll, Roll,
/// Marquer des points /// Marquer les points
Mark { points: u8 }, Mark,
/// Continuer après avoir gagné un trou /// Continuer après avoir gagné un trou
Go, Go,
/// Effectuer un mouvement de pions /// Effectuer un mouvement de pions
Move { Move {
move1: (usize, usize), // (from, to) pour le premier pion
move2: (usize, usize), // (from, to) pour le deuxième pion
},
}
/// Actions compactes basées sur le contexte du jeu
/// Réduit drastiquement l'espace d'actions en utilisant l'état du jeu
#[derive(Debug, Clone, Serialize, Deserialize, PartialEq)]
pub enum CompactAction {
/// Lancer les dés
Roll,
/// Marquer des points (0-12)
Mark { points: u8 },
/// Continuer après avoir gagné un trou
Go,
/// Choix de mouvement simplifié
MoveChoice {
dice_order: bool, // true = utiliser dice[0] en premier, false = dice[1] en premier dice_order: bool, // true = utiliser dice[0] en premier, false = dice[1] en premier
from1: usize, // position de départ du premier pion (0-24) from1: usize, // position de départ du premier pion (0-24)
from2: usize, // position de départ du deuxième pion (0-24) from2: usize, // position de départ du deuxième pion (0-24)
}, },
} }
impl CompactAction {
/// Convertit CompactAction vers TrictracAction en utilisant l'état du jeu
pub fn to_trictrac_action(&self, game_state: &crate::GameState) -> Option<TrictracAction> {
match self {
CompactAction::Roll => Some(TrictracAction::Roll),
CompactAction::Mark { points } => Some(TrictracAction::Mark { points: *points }),
CompactAction::Go => Some(TrictracAction::Go),
CompactAction::MoveChoice { dice_order, from1, from2 } => {
// Calculer les positions de destination basées sur les dés
if let Some(player_color) = game_state.player_color_by_id(&game_state.active_player_id) {
let dice = game_state.dice;
let (die1, die2) = if *dice_order { (dice.values.0, dice.values.1) } else { (dice.values.1, dice.values.0) };
// Calculer les destinations (simplifiée - à adapter selon les règles de mouvement)
let to1 = if player_color == store::Color::White {
from1 + die1 as usize
} else {
from1.saturating_sub(die1 as usize)
};
let to2 = if player_color == store::Color::White {
from2 + die2 as usize
} else {
from2.saturating_sub(die2 as usize)
};
Some(TrictracAction::Move {
move1: (*from1, to1),
move2: (*from2, to2),
})
} else {
None
}
}
}
}
/// Taille de l'espace d'actions compactes selon le contexte
pub fn context_action_space_size(game_state: &crate::GameState) -> usize {
use store::TurnStage;
match game_state.turn_stage {
TurnStage::RollDice | TurnStage::RollWaiting => 1, // Seulement Roll
TurnStage::MarkPoints | TurnStage::MarkAdvPoints => 13, // Mark 0-12 points
TurnStage::HoldOrGoChoice => {
// Go + mouvements possibles
if let Some(player_color) = game_state.player_color_by_id(&game_state.active_player_id) {
let rules = store::MoveRules::new(&player_color, &game_state.board, game_state.dice);
let possible_moves = rules.get_possible_moves_sequences(true, vec![]);
1 + Self::estimate_compact_moves(game_state, &possible_moves)
} else {
1
}
}
TurnStage::Move => {
// Seulement les mouvements
if let Some(player_color) = game_state.player_color_by_id(&game_state.active_player_id) {
let rules = store::MoveRules::new(&player_color, &game_state.board, game_state.dice);
let possible_moves = rules.get_possible_moves_sequences(true, vec![]);
Self::estimate_compact_moves(game_state, &possible_moves)
} else {
0
}
}
}
}
/// Estime le nombre d'actions compactes pour les mouvements
fn estimate_compact_moves(game_state: &crate::GameState, _possible_moves: &[(store::CheckerMove, store::CheckerMove)]) -> usize {
// Au lieu d'encoder tous les mouvements possibles,
// on utilise : 2 (ordre des dés) * 25 (from1) * 25 (from2) = 1250 maximum
// En pratique, beaucoup moins car on ne peut partir que des positions avec des pions
let max_dice_orders = if game_state.dice.values.0 != game_state.dice.values.1 { 2 } else { 1 };
let _max_positions = 25; // positions 0-24
// Estimation conservatrice : environ 10 positions de départ possibles en moyenne
max_dice_orders * 10 * 10 // ≈ 200 au lieu de 331,791
}
}
impl TrictracAction { impl TrictracAction {
/// Encode une action en index pour le réseau de neurones /// Encode une action en index pour le réseau de neurones
pub fn to_action_index(&self) -> usize { pub fn to_action_index(&self) -> usize {
match self { match self {
TrictracAction::Roll => 0, TrictracAction::Roll => 0,
TrictracAction::Mark { points } => { TrictracAction::Mark => 1,
1 + (*points as usize).min(12) // Indices 1-13 pour 0-12 points TrictracAction::Go => 2,
} TrictracAction::Move {
TrictracAction::Go => 14, dice_order,
TrictracAction::Move { move1, move2 } => { from1,
from2,
} => {
// Encoder les mouvements dans l'espace d'actions // Encoder les mouvements dans l'espace d'actions
// Indices 15+ pour les mouvements // Indices 3+ pour les mouvements
15 + encode_move_pair(*move1, *move2) let mut start = 3;
if !dice_order {
// 25 * 25 = 625
start += 625;
}
start + from1 * 25 + from2
} }
} }
} }
@ -136,51 +48,62 @@ impl TrictracAction {
pub fn from_action_index(index: usize) -> Option<TrictracAction> { pub fn from_action_index(index: usize) -> Option<TrictracAction> {
match index { match index {
0 => Some(TrictracAction::Roll), 0 => Some(TrictracAction::Roll),
1..=13 => Some(TrictracAction::Mark { 1 => Some(TrictracAction::Mark),
points: (index - 1) as u8, 2 => Some(TrictracAction::Go),
}), i if i >= 3 => {
14 => Some(TrictracAction::Go), let move_code = i - 3;
i if i >= 15 => { let (dice_order, from1, from2) = Self::decode_move(move_code);
let move_code = i - 15; Some(TrictracAction::Move {
let (move1, move2) = decode_move_pair(move_code); dice_order,
Some(TrictracAction::Move { move1, move2 }) from1,
from2,
})
} }
_ => None, _ => None,
} }
} }
/// Décode un entier en paire de mouvements
fn decode_move(code: usize) -> (bool, usize, usize) {
let mut encoded = code;
let dice_order = code < 626;
if !dice_order {
encoded -= 625
}
let from1 = encoded / 25;
let from2 = encoded % 25;
(dice_order, from1, from2)
}
/// Retourne la taille de l'espace d'actions total /// Retourne la taille de l'espace d'actions total
pub fn action_space_size() -> usize { pub fn action_space_size() -> usize {
// 1 (Roll) + 13 (Mark 0-12) + 1 (Go) + mouvements possibles // 1 (Roll) + 1 (Mark) + 1 (Go) + mouvements possibles
// Pour les mouvements : 25*25*25*25 = 390625 (position 0-24 pour chaque from/to) // Pour les mouvements : 2*25*25 = 1250 (choix du dé + position 0-24 pour chaque from)
// Mais on peut optimiser en limitant aux positions valides (1-24) // Mais on peut optimiser en limitant aux positions valides (1-24)
15 + (24 * 24 * 24 * 24) // = 331791 3 + (2 * 25 * 25) // = 1253
}
} }
/// Encode une paire de mouvements en un seul entier // pub fn to_game_event(&self, player_id: PlayerId, dice: Dice) -> GameEvent {
fn encode_move_pair(move1: (usize, usize), move2: (usize, usize)) -> usize { // match action {
let (from1, to1) = move1; // TrictracAction::Roll => Some(GameEvent::Roll { player_id }),
let (from2, to2) = move2; // TrictracAction::Mark => Some(GameEvent::Mark { player_id, points }),
// Assurer que les positions sont dans la plage 0-24 // TrictracAction::Go => Some(GameEvent::Go { player_id }),
let from1 = from1.min(24); // TrictracAction::Move {
let to1 = to1.min(24); // dice_order,
let from2 = from2.min(24); // from1,
let to2 = to2.min(24); // from2,
// } => {
from1 * (25 * 25 * 25) + to1 * (25 * 25) + from2 * 25 + to2 // // Effectuer un mouvement
} // let checker_move1 = store::CheckerMove::new(move1.0, move1.1).unwrap_or_default();
// let checker_move2 = store::CheckerMove::new(move2.0, move2.1).unwrap_or_default();
/// Décode un entier en paire de mouvements //
fn decode_move_pair(code: usize) -> ((usize, usize), (usize, usize)) { // Some(GameEvent::Move {
let from1 = code / (25 * 25 * 25); // player_id: self.agent_player_id,
let remainder = code % (25 * 25 * 25); // moves: (checker_move1, checker_move2),
let to1 = remainder / (25 * 25); // })
let remainder = remainder % (25 * 25); // }
let from2 = remainder / 25; // };
let to2 = remainder % 25; // }
((from1, to1), (from2, to2))
} }
/// Configuration pour l'agent DQN /// Configuration pour l'agent DQN
@ -350,17 +273,7 @@ pub fn get_valid_actions(game_state: &crate::GameState) -> Vec<TrictracAction> {
valid_actions.push(TrictracAction::Roll); valid_actions.push(TrictracAction::Roll);
} }
TurnStage::MarkPoints | TurnStage::MarkAdvPoints => { TurnStage::MarkPoints | TurnStage::MarkAdvPoints => {
// Calculer les points possibles valid_actions.push(TrictracAction::Mark);
if let Some(player) = game_state.players.get(&active_player_id) {
let dice_roll_count = player.dice_roll_count;
let points_rules = PointsRules::new(&color, &game_state.board, game_state.dice);
let (max_points, _) = points_rules.get_points(dice_roll_count);
// Permettre de marquer entre 0 et max_points
for points in 0..=max_points {
valid_actions.push(TrictracAction::Mark { points });
}
}
} }
TurnStage::HoldOrGoChoice => { TurnStage::HoldOrGoChoice => {
valid_actions.push(TrictracAction::Go); valid_actions.push(TrictracAction::Go);
@ -370,9 +283,11 @@ pub fn get_valid_actions(game_state: &crate::GameState) -> Vec<TrictracAction> {
let possible_moves = rules.get_possible_moves_sequences(true, vec![]); let possible_moves = rules.get_possible_moves_sequences(true, vec![]);
for (move1, move2) in possible_moves { for (move1, move2) in possible_moves {
let diff_move1 = move1.get_to() - move1.get_from();
valid_actions.push(TrictracAction::Move { valid_actions.push(TrictracAction::Move {
move1: (move1.get_from(), move1.get_to()), dice_order: diff_move1 == game_state.dice.values.0 as usize,
move2: (move2.get_from(), move2.get_to()), from1: move1.get_from(),
from2: move2.get_from(),
}); });
} }
} }
@ -381,9 +296,11 @@ pub fn get_valid_actions(game_state: &crate::GameState) -> Vec<TrictracAction> {
let possible_moves = rules.get_possible_moves_sequences(true, vec![]); let possible_moves = rules.get_possible_moves_sequences(true, vec![]);
for (move1, move2) in possible_moves { for (move1, move2) in possible_moves {
let diff_move1 = move1.get_to() - move1.get_from();
valid_actions.push(TrictracAction::Move { valid_actions.push(TrictracAction::Move {
move1: (move1.get_from(), move1.get_to()), dice_order: diff_move1 == game_state.dice.values.0 as usize,
move2: (move2.get_from(), move2.get_to()), from1: move1.get_from(),
from2: move2.get_from(),
}); });
} }
} }
@ -393,92 +310,6 @@ pub fn get_valid_actions(game_state: &crate::GameState) -> Vec<TrictracAction> {
valid_actions valid_actions
} }
/// Génère les actions compactes valides selon l'état du jeu
pub fn get_valid_compact_actions(game_state: &crate::GameState) -> Vec<CompactAction> {
use crate::PointsRules;
use store::TurnStage;
let mut valid_actions = Vec::new();
let active_player_id = game_state.active_player_id;
let player_color = game_state.player_color_by_id(&active_player_id);
if let Some(color) = player_color {
match game_state.turn_stage {
TurnStage::RollDice | TurnStage::RollWaiting => {
valid_actions.push(CompactAction::Roll);
}
TurnStage::MarkPoints | TurnStage::MarkAdvPoints => {
// Calculer les points possibles
if let Some(player) = game_state.players.get(&active_player_id) {
let dice_roll_count = player.dice_roll_count;
let points_rules = PointsRules::new(&color, &game_state.board, game_state.dice);
let (max_points, _) = points_rules.get_points(dice_roll_count);
// Permettre de marquer entre 0 et max_points
for points in 0..=max_points {
valid_actions.push(CompactAction::Mark { points });
}
}
}
TurnStage::HoldOrGoChoice => {
valid_actions.push(CompactAction::Go);
// Ajouter les choix de mouvements compacts
add_compact_move_actions(game_state, &color, &mut valid_actions);
}
TurnStage::Move => {
// Seulement les mouvements compacts
add_compact_move_actions(game_state, &color, &mut valid_actions);
}
}
}
valid_actions
}
/// Ajoute les actions de mouvement compactes basées sur le contexte
fn add_compact_move_actions(game_state: &crate::GameState, color: &store::Color, valid_actions: &mut Vec<CompactAction>) {
let rules = store::MoveRules::new(color, &game_state.board, game_state.dice);
let possible_moves = rules.get_possible_moves_sequences(true, vec![]);
// Extraire les positions de départ uniques des mouvements possibles
let mut valid_from_positions = std::collections::HashSet::new();
for (move1, move2) in &possible_moves {
valid_from_positions.insert(move1.get_from());
valid_from_positions.insert(move2.get_from());
}
let dice = game_state.dice;
let dice_orders = if dice.values.0 != dice.values.1 { vec![true, false] } else { vec![true] };
// Générer les combinaisons compactes valides
for dice_order in dice_orders {
for &from1 in &valid_from_positions {
for &from2 in &valid_from_positions {
// Vérifier si cette combinaison produit un mouvement valide
let compact_action = CompactAction::MoveChoice {
dice_order,
from1,
from2
};
if let Some(trictrac_action) = compact_action.to_trictrac_action(game_state) {
// Vérifier si ce mouvement est dans la liste des mouvements possibles
if let TrictracAction::Move { move1, move2 } = trictrac_action {
if let (Ok(checker_move1), Ok(checker_move2)) =
(store::CheckerMove::new(move1.0, move1.1), store::CheckerMove::new(move2.0, move2.1)) {
if possible_moves.contains(&(checker_move1, checker_move2)) {
valid_actions.push(compact_action);
}
}
}
}
}
}
}
}
/// Retourne les indices des actions valides /// Retourne les indices des actions valides
pub fn get_valid_action_indices(game_state: &crate::GameState) -> Vec<usize> { pub fn get_valid_action_indices(game_state: &crate::GameState) -> Vec<usize> {
get_valid_actions(game_state) get_valid_actions(game_state)

6
bot/src/strategy/dqn_trainer.rs
View file

@ -266,7 +266,11 @@ impl TrictracEnv {
player_id: self.agent_player_id, player_id: self.agent_player_id,
}) })
} }
TrictracAction::Move { move1, move2 } => { TrictracAction::Move {
dice_order,
from1,
from2,
} => {
// Effectuer un mouvement // Effectuer un mouvement
let checker_move1 = store::CheckerMove::new(move1.0, move1.1).unwrap_or_default(); let checker_move1 = store::CheckerMove::new(move1.0, move1.1).unwrap_or_default();
let checker_move2 = store::CheckerMove::new(move2.0, move2.1).unwrap_or_default(); let checker_move2 = store::CheckerMove::new(move2.0, move2.1).unwrap_or_default();

25
doc/workflow.md Normal file
View file

@ -0,0 +1,25 @@
# Workflow
@startuml
state c <<choice>>
state haswon <<choice>>
state MarkPoints #lightblue
state MarkAdvPoints #lightblue
note right of MarkPoints : automatic 'Mark' transition\nwhen no school
note right of MarkAdvPoints : automatic 'Mark' transition\nwhen no school
[*] -> RollDice : BeginGame
RollDice --> RollWaiting : Roll (current player)
RollWaiting --> MarkPoints : RollResult (engine)
MarkPoints --> c : Mark (current player)
c --> HoldHorGoChoice : [new hole]
c --> [*] : [has won]
c --> Move : [not new hole]
HoldHorGoChoice --> RollDice : Go
HoldHorGoChoice --> MarkAdvPoints : Move
Move --> MarkAdvPoints : Move
MarkAdvPoints --> haswon : Mark (adversary)
haswon --> RollDice : [has not won]
haswon --> [*] : [has won]
@enduml

15
store/src/game.rs
View file

@ -71,7 +71,7 @@ pub struct GameState {
/// last dice pair rolled /// last dice pair rolled
pub dice: Dice, pub dice: Dice,
/// players points computed for the last dice pair rolled /// players points computed for the last dice pair rolled
dice_points: (u8, u8), pub dice_points: (u8, u8),
pub dice_moves: (CheckerMove, CheckerMove), pub dice_moves: (CheckerMove, CheckerMove),
pub dice_jans: PossibleJans, pub dice_jans: PossibleJans,
/// true if player needs to roll first /// true if player needs to roll first
@ -505,14 +505,8 @@ impl GameState {
self.players.remove(player_id); self.players.remove(player_id);
} }
Roll { player_id: _ } => { Roll { player_id: _ } => {
// Opponent has moved, we can mark pending points earned during opponent's turn
let new_hole = self.mark_points(self.active_player_id, self.dice_points.1);
if new_hole && self.get_active_player().unwrap().holes > 12 {
self.stage = Stage::Ended;
} else {
self.turn_stage = TurnStage::RollWaiting; self.turn_stage = TurnStage::RollWaiting;
} }
}
RollResult { player_id: _, dice } => { RollResult { player_id: _, dice } => {
self.dice = *dice; self.dice = *dice;
self.inc_roll_count(self.active_player_id); self.inc_roll_count(self.active_player_id);
@ -534,6 +528,7 @@ impl GameState {
} }
} }
Mark { player_id, points } => { Mark { player_id, points } => {
if self.schools_enabled {
let new_hole = self.mark_points(*player_id, *points); let new_hole = self.mark_points(*player_id, *points);
if new_hole { if new_hole {
if self.get_active_player().unwrap().holes > 12 { if self.get_active_player().unwrap().holes > 12 {
@ -553,6 +548,7 @@ impl GameState {
}; };
} }
} }
}
Go { player_id: _ } => self.new_pick_up(), Go { player_id: _ } => self.new_pick_up(),
Move { player_id, moves } => { Move { player_id, moves } => {
let player = self.players.get(player_id).unwrap(); let player = self.players.get(player_id).unwrap();
@ -563,6 +559,11 @@ impl GameState {
self.turn_stage = if self.schools_enabled { self.turn_stage = if self.schools_enabled {
TurnStage::MarkAdvPoints TurnStage::MarkAdvPoints
} else { } else {
// The player has moved, we can mark its opponent's points (which is now the current player)
let new_hole = self.mark_points(self.active_player_id, self.dice_points.1);
if new_hole && self.get_active_player().unwrap().holes > 12 {
self.stage = Stage::Ended;
}
TurnStage::RollDice TurnStage::RollDice
}; };
} }