# DQN Best Hyperparameters
# Source: Historical training + manual tuning
# Date: 2025-11-02
# Status: PENDING - Awaiting hyperopt completion for optimal values
# Dataset: ES_FUT_180d.parquet

# NOTE: These are conservative defaults based on successful training runs.
# After completing DQN hyperopt (with action-dependent rewards fix), update
# this file with optimal parameters from the best trial.

# Learning Parameters
learning_rate = 0.0001           # Conservative LR for stable convergence
batch_size = 128                 # Optimal for RTX 3050 Ti 4GB (max 230)
gamma = 0.99                     # Discount factor (standard RL)

# Exploration Schedule (Epsilon-Greedy)
epsilon_start = 1.0              # Start with full exploration
epsilon_end = 0.01               # Minimum exploration (1%)
epsilon_decay = 0.995            # Decay rate per episode

# Replay Buffer Configuration
buffer_size = 100000             # Experience replay capacity
min_replay_size = 1000           # Minimum experiences before training

# Branching DQN (Tavakoli et al., 2018)
branch_hidden_dim = 128

# Training Configuration
epochs = 100                     # Training epochs (default)
checkpoint_frequency = 10        # Save every 10 epochs

# Early Stopping Configuration
early_stopping_enabled = true
q_value_floor = 0.5              # Minimum Q-value threshold
min_loss_improvement_pct = 2.0   # Minimum 2% improvement over window
plateau_window = 30              # Epochs to check for plateau
min_epochs_before_stopping = 50  # Minimum training duration

# GPU Configuration
# Max batch size for RTX 3050 Ti 4GB: 230
# Max batch size for RTX A4000 16GB: 512+
# Recommended: 128 (safe for all GPUs)

# Historical Performance Notes
# - Training time: ~15s for 50 epochs (RTX 3050 Ti)
# - GPU memory: ~6MB model size
# - Inference: ~200μs per action
# - Tests: 16/16 passing (100% coverage)

# Known Issues (FIXED as of 2025-11-02)
# ✅ Action-dependent rewards implemented (lines 722-743, trainers/dqn.rs)
# ✅ Hyperopt objective fixed to maximize episode rewards (not loss)
# ✅ 16 comprehensive tests added (dqn_action_dependent_reward_test.rs)
# ⏳ Awaiting hyperopt deployment to find optimal hyperparameters

# Deployment
# After hyperopt completes, update this file with:
# - Optimal batch_size (expected: 128-512)
# - Optimal learning_rate (expected: 1e-5 to 1e-3)
# - Optimal gamma (expected: 0.95-0.99)
# - Optimal epsilon_decay (expected: 0.99-0.999)

# Related Files
# - DQN_ACTION_DEPENDENT_REWARDS_FIX_SUMMARY.md: Fix documentation
# - DQN_HYPEROPT_CORRECTED_QUICKREF.md: Hyperopt guide
# - ml/src/trainers/dqn.rs: Trainer implementation
# - deploy_dqn_hyperopt_corrected.sh: Deployment script