feat: add 10 new ML models for auction optimization (Phases 1-6)

Phase 1 - Quick Wins:
- QuantileEnsemble: P10/P50/P90 predictions for risk-aware bidding
- MinutesSurvivalModel: Weibull AFT for minutes distribution modeling

Phase 2 - Adaptive Auction:
- BanditAuctionSolver: Thompson Sampling for live auction bids
- OpponentBidModel: Predict competitor bids via LightGBM
- BudgetOptimizer: Bayesian optimization for role-level allocation

Phase 3 - Deep Learning:
- RLAuctionPolicy: Double DQN agent for auction strategy
- SetTransformer: Team composition valuation via set-based ML

Phase 4 - Probabilistic:
- BayesianPlayerModel: Hierarchical pooling for rookie uncertainty
- ConformalPredictor: Calibrated prediction intervals

Phase 5 - Chemistry & Form:
- PlayerChemistryGAT: Graph attention network for player synergies
- PlayerFormModel: Hawkes process for form momentum

Phase 6 - Causal:
- TransferCausalModel: Causal forest for transfer effects
- AuctionEffectAnalyzer: Bid adjustment from causal analysis

81 tests passing

src/optimization/__init__.py

@@ -1 +1,14 @@
 """Optimization modules for auction and lineup selection."""
+
+from .auction_solver import AuctionSolver, AuctionConfig, PlayerValuation
+from .lineup_solver import LineupSolver, LineupConstraints, PlayerScore, MCTSNode
+from .opponent_model import OpponentModel
+from .transfer_analyzer import TransferAnalyzer
+
+# Phase 2: Bandit, opponent bidding, budget optimization
+from .bandit_auction import BanditAuctionSolver
+from .opponent_bidding_model import OpponentBidModel
+from .budget_optimizer import BudgetOptimizer
+
+# Phase 3: Reinforcement learning auction agent
+from .rl_auction_agent import AuctionEnv, RLAuctionPolicy, RLAuctionTrainer, QNetwork