auto train
This commit is contained in:
@@ -0,0 +1,55 @@
|
||||
using JoshHeaps.Net.Services.Interfaces;
|
||||
|
||||
namespace JoshHeaps.Net.Services.Implementations;
|
||||
|
||||
/// <summary>
|
||||
/// Continuously trains the learned engine in the background: two self-play games run in
|
||||
/// parallel, the learned engine (skill 6) against Stockfish (skill 20), one with Stockfish as
|
||||
/// black and one as white. Each slot is independent — when its game finishes it immediately
|
||||
/// starts another under the same conditions, without waiting on the other slot. Registered
|
||||
/// only outside Development and gated by the ChessEngine:AutoTrain config flag.
|
||||
/// </summary>
|
||||
public sealed class AutoTrainingService(
|
||||
ISelfPlayCoordinator coordinator,
|
||||
ILogger<AutoTrainingService> logger) : BackgroundService
|
||||
{
|
||||
private const int LearnedSkill = 6;
|
||||
private const int StockfishSkill = 20;
|
||||
private static readonly TimeSpan _restartBackoff = TimeSpan.FromSeconds(5);
|
||||
|
||||
protected override Task ExecuteAsync(CancellationToken stoppingToken)
|
||||
{
|
||||
// Learned plays both colors so the model trains symmetrically; each slot is its own loop.
|
||||
var stockfishBlack = RunSlot(
|
||||
new SelfPlayConfig(ChessEngineKind.CustomLearned, LearnedSkill, ChessEngineKind.Stockfish, StockfishSkill),
|
||||
stoppingToken);
|
||||
var stockfishWhite = RunSlot(
|
||||
new SelfPlayConfig(ChessEngineKind.Stockfish, StockfishSkill, ChessEngineKind.CustomLearned, LearnedSkill),
|
||||
stoppingToken);
|
||||
|
||||
return Task.WhenAll(stockfishBlack, stockfishWhite);
|
||||
}
|
||||
|
||||
private async Task RunSlot(SelfPlayConfig config, CancellationToken stoppingToken)
|
||||
{
|
||||
while (!stoppingToken.IsCancellationRequested)
|
||||
{
|
||||
try
|
||||
{
|
||||
await coordinator.StartGame(config, stoppingToken).Completion;
|
||||
}
|
||||
catch (OperationCanceledException)
|
||||
{
|
||||
break;
|
||||
}
|
||||
catch (Exception ex)
|
||||
{
|
||||
// Most likely an engine failing to start (e.g. Stockfish). Back off so a
|
||||
// persistent failure doesn't spin a tight loop, then try again.
|
||||
logger.LogError(ex, "Auto-training game failed to start; retrying after backoff.");
|
||||
try { await Task.Delay(_restartBackoff, stoppingToken); }
|
||||
catch (OperationCanceledException) { break; }
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -29,6 +29,13 @@ public sealed class ChessEngineOptions
|
||||
/// clashes. Override via the <c>ChessEngine__WeightsPath</c> environment variable.
|
||||
/// </summary>
|
||||
public string? WeightsPath { get; set; }
|
||||
|
||||
/// <summary>
|
||||
/// When true (and outside Development), a background service continuously plays the learned
|
||||
/// engine against Stockfish to train it. Set to false to stop auto-training without a
|
||||
/// redeploy. Override via the <c>ChessEngine__AutoTrain</c> environment variable.
|
||||
/// </summary>
|
||||
public bool AutoTrain { get; set; } = true;
|
||||
}
|
||||
|
||||
/// <summary>Creates the configured <see cref="IChessEngine"/> per game.</summary>
|
||||
|
||||
@@ -0,0 +1,69 @@
|
||||
using System.Collections.Concurrent;
|
||||
using JoshHeaps.Net.Models;
|
||||
using JoshHeaps.Net.Services.Interfaces;
|
||||
|
||||
namespace JoshHeaps.Net.Services.Implementations;
|
||||
|
||||
/// <summary>
|
||||
/// In-memory game registry with a delayed-removal lifecycle. Singleton: the game state is
|
||||
/// process-wide, not per-request, so it lives in a service rather than static controller fields.
|
||||
/// </summary>
|
||||
public sealed class GameStore(ILearnedWeightsStore weightsStore) : IGameStore
|
||||
{
|
||||
private readonly ConcurrentDictionary<Guid, GameState> _games = [];
|
||||
private readonly ConcurrentDictionary<Guid, Task> _removalTasks = [];
|
||||
private readonly ConcurrentDictionary<Guid, CancellationTokenSource> _removalCts = [];
|
||||
|
||||
public void Add(GameState game) => _games[game.GameId] = game;
|
||||
|
||||
public bool TryGet(Guid id, out GameState game) => _games.TryGetValue(id, out game!);
|
||||
|
||||
public bool Contains(Guid id) => _games.ContainsKey(id);
|
||||
|
||||
public IReadOnlyCollection<GameState> All => [.. _games.Values];
|
||||
|
||||
public void ScheduleRemove(Guid id, TimeSpan delay)
|
||||
{
|
||||
if (_removalCts.TryRemove(id, out var oldCts))
|
||||
{
|
||||
oldCts.Cancel();
|
||||
oldCts.Dispose();
|
||||
}
|
||||
|
||||
var cts = new CancellationTokenSource();
|
||||
_removalCts[id] = cts;
|
||||
|
||||
_removalTasks[id] = Task.Run(async () =>
|
||||
{
|
||||
try
|
||||
{
|
||||
await Task.Delay(delay, cts.Token);
|
||||
|
||||
if (_games.TryGetValue(id, out var game))
|
||||
{
|
||||
if (game.WhiteComputer is not null)
|
||||
await game.WhiteComputer.DisposeAsync();
|
||||
if (game.BlackComputer is not null)
|
||||
await game.BlackComputer.DisposeAsync();
|
||||
|
||||
// Free the trainer if the game never reached ApplyLearning (e.g. timed out).
|
||||
if (game.Trainer != nint.Zero)
|
||||
{
|
||||
weightsStore.DestroyTrainer(game.Trainer);
|
||||
game.Trainer = nint.Zero;
|
||||
}
|
||||
}
|
||||
|
||||
_games.Remove(id, out _);
|
||||
}
|
||||
catch (OperationCanceledException) { }
|
||||
finally
|
||||
{
|
||||
if (_removalCts.TryGetValue(id, out var currentCts) && currentCts == cts)
|
||||
_removalCts.TryRemove(id, out _);
|
||||
|
||||
cts.Dispose();
|
||||
}
|
||||
});
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,189 @@
|
||||
using JoshHeaps.Net.Models;
|
||||
using JoshHeaps.Net.Services.Interfaces;
|
||||
|
||||
namespace JoshHeaps.Net.Services.Implementations;
|
||||
|
||||
/// <summary>
|
||||
/// Runs CPU-vs-CPU games: builds the game and engines, plays a randomized opening (for training
|
||||
/// variety), drives the move loop to completion, then trains the learned engine from the result.
|
||||
/// </summary>
|
||||
public sealed class SelfPlayCoordinator(
|
||||
IChessService chessService,
|
||||
IChessEngineFactory engineFactory,
|
||||
IComputerMoveOrchestrator orchestrator,
|
||||
ILearnedWeightsStore weightsStore,
|
||||
IGameStore gameStore) : ISelfPlayCoordinator
|
||||
{
|
||||
private static readonly TimeSpan _computerGameTimeout = TimeSpan.FromHours(1);
|
||||
private static readonly TimeSpan _selfPlayMoveDelay = TimeSpan.FromSeconds(1);
|
||||
private static readonly TimeSpan _selfPlayResultTimeout = TimeSpan.FromSeconds(30);
|
||||
|
||||
// Plies of random legal moves at the start of a training game, so self-play and
|
||||
// engine-vs-engine games explore different lines instead of replaying one game.
|
||||
private const int _openingRandomPlies = 4;
|
||||
|
||||
public (Guid GameId, Task Completion) StartGame(SelfPlayConfig config, CancellationToken cancellationToken = default)
|
||||
{
|
||||
var whiteComputer = engineFactory.Create(config.WhiteSkill, config.WhiteKind);
|
||||
IChessEngine blackComputer;
|
||||
try
|
||||
{
|
||||
blackComputer = engineFactory.Create(config.BlackSkill, config.BlackKind);
|
||||
}
|
||||
catch
|
||||
{
|
||||
// Don't leak the first engine if the second fails to start (e.g. Stockfish process).
|
||||
whiteComputer.DisposeAsync().AsTask().GetAwaiter().GetResult();
|
||||
throw;
|
||||
}
|
||||
|
||||
var gameState = chessService.CreateNewGame();
|
||||
gameState.IsVsComputer = true;
|
||||
gameState.IsComputerVsComputer = true;
|
||||
gameState.WhiteJoined = true;
|
||||
gameState.BlackJoined = true;
|
||||
gameState.WhitePlayerId = Guid.NewGuid();
|
||||
gameState.BlackPlayerId = Guid.NewGuid();
|
||||
gameState.WhiteEngineKind = config.WhiteKind;
|
||||
gameState.BlackEngineKind = config.BlackKind;
|
||||
gameState.WhiteComputer = whiteComputer;
|
||||
gameState.BlackComputer = blackComputer;
|
||||
|
||||
// When the learned engine is playing, attach a trainer so the outcome can train it.
|
||||
if (config.WhiteKind == ChessEngineKind.CustomLearned || config.BlackKind == ChessEngineKind.CustomLearned)
|
||||
gameState.Trainer = weightsStore.CreateTrainer();
|
||||
|
||||
gameStore.Add(gameState);
|
||||
gameStore.ScheduleRemove(gameState.GameId, _computerGameTimeout);
|
||||
|
||||
var completion = Task.Run(() => RunAsync(gameState, cancellationToken));
|
||||
return (gameState.GameId, completion);
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Drives the game to completion, then trains from it. Never throws — a failure just ends
|
||||
/// the game (and the trainer is always freed), so callers can safely await or ignore it.
|
||||
/// </summary>
|
||||
private async Task RunAsync(GameState gameState, CancellationToken cancellationToken)
|
||||
{
|
||||
try
|
||||
{
|
||||
// Give spectators a moment to join the SignalR group before the first move.
|
||||
await Task.Delay(_selfPlayMoveDelay, cancellationToken);
|
||||
|
||||
// Training games open with random moves so they don't replay the same line.
|
||||
if (gameState.Trainer != nint.Zero)
|
||||
for (int i = 0; i < _openingRandomPlies && IsLive(gameState, cancellationToken); i++)
|
||||
{
|
||||
await orchestrator.PlayRandomMoveAsync(gameState);
|
||||
await Task.Delay(_selfPlayMoveDelay, cancellationToken);
|
||||
}
|
||||
|
||||
while (IsLive(gameState, cancellationToken))
|
||||
{
|
||||
await orchestrator.PlayAsync(gameState);
|
||||
await Task.Delay(_selfPlayMoveDelay, cancellationToken);
|
||||
}
|
||||
}
|
||||
catch (OperationCanceledException) { /* service shutting down */ }
|
||||
catch (Exception ex)
|
||||
{
|
||||
Console.WriteLine($"Self-play game {gameState.GameId} stopped: {ex.Message}");
|
||||
}
|
||||
|
||||
ApplyLearning(gameState);
|
||||
|
||||
// Leave the finished game in place briefly so spectators can see the result.
|
||||
if (gameStore.Contains(gameState.GameId))
|
||||
gameStore.ScheduleRemove(gameState.GameId, _selfPlayResultTimeout);
|
||||
}
|
||||
|
||||
private bool IsLive(GameState gameState, CancellationToken cancellationToken) =>
|
||||
!cancellationToken.IsCancellationRequested
|
||||
&& gameStore.Contains(gameState.GameId)
|
||||
&& !IsGameOver(gameState);
|
||||
|
||||
private static bool IsGameOver(GameState gameState) =>
|
||||
gameState.IsCheckmate || gameState.IsStalemate || gameState.IsThreefoldRepetition || gameState.IsForfeited;
|
||||
|
||||
/// <summary>
|
||||
/// Feeds a finished training game's result into the learned weights, then frees the trainer.
|
||||
/// A checkmate is a full-strength result; a material-imbalance draw is a half-strength win
|
||||
/// for the lower-material side (holding a draw while down material is a success; only drawing
|
||||
/// while up is a failure). A balanced draw, forfeit, or unfinished game teaches nothing.
|
||||
/// </summary>
|
||||
private void ApplyLearning(GameState gameState)
|
||||
{
|
||||
if (gameState.Trainer == nint.Zero)
|
||||
return;
|
||||
|
||||
if (TryDetermineOutcome(gameState, out var winner, out var weight))
|
||||
weightsStore.ApplyResult(gameState.Trainer, winner, weight);
|
||||
|
||||
weightsStore.DestroyTrainer(gameState.Trainer);
|
||||
gameState.Trainer = nint.Zero;
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Determines the trainable outcome of a finished game: the winning color and the reward
|
||||
/// weight. Returns false when the game teaches nothing (balanced draw, forfeit, unfinished).
|
||||
/// </summary>
|
||||
private static bool TryDetermineOutcome(GameState gameState, out PieceColor winner, out double weight)
|
||||
{
|
||||
winner = PieceColor.White;
|
||||
weight = 1.0;
|
||||
|
||||
if (gameState.IsCheckmate)
|
||||
{
|
||||
// The side to move is the mated one, so the winner is the other color.
|
||||
winner = gameState.CurrentPlayer == PieceColor.White ? PieceColor.Black : PieceColor.White;
|
||||
return true;
|
||||
}
|
||||
|
||||
if (gameState.IsStalemate || gameState.IsThreefoldRepetition)
|
||||
{
|
||||
var (white, black) = MaterialCounts(gameState);
|
||||
|
||||
if (white == black)
|
||||
return false; // a balanced draw carries no signal
|
||||
|
||||
winner = white < black ? PieceColor.White : PieceColor.Black;
|
||||
weight = 0.5;
|
||||
return true;
|
||||
}
|
||||
|
||||
return false; // forfeit / unfinished
|
||||
}
|
||||
|
||||
/// <summary>Total non-king material per side (P=1, N=B=3, R=5, Q=9), for draw adjudication.</summary>
|
||||
private static (int white, int black) MaterialCounts(GameState gameState)
|
||||
{
|
||||
int white = 0, black = 0;
|
||||
|
||||
for (int row = 0; row < 8; row++)
|
||||
for (int col = 0; col < 8; col++)
|
||||
{
|
||||
var piece = gameState.Board[row, col];
|
||||
|
||||
if (piece is null)
|
||||
continue;
|
||||
|
||||
int value = piece.Type switch
|
||||
{
|
||||
PieceType.Pawn => 1,
|
||||
PieceType.Knight => 3,
|
||||
PieceType.Bishop => 3,
|
||||
PieceType.Rook => 5,
|
||||
PieceType.Queen => 9,
|
||||
_ => 0
|
||||
};
|
||||
|
||||
if (piece.Color == PieceColor.White)
|
||||
white += value;
|
||||
else
|
||||
black += value;
|
||||
}
|
||||
|
||||
return (white, black);
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user