feat: reward config pipeline — DQNHyperparameters + TOML profiles

Add 7 composite reward fields to DQNHyperparameters: w_dsr, w_pnl,
w_dd, w_idle, dd_threshold, loss_aversion, time_decay_rate.

Add RewardSection to training_profile.rs with Option<f64> fields and
apply_to() mapping. Add [reward] section to all 3 DQN TOML profiles
(production, smoketest, hyperopt) with identical defaults.

Remove hold_reward from ExperienceSection (replaced by w_idle).
Add 7 reward search bounds to SearchSpaceSection and bound() match.
Add 7 reward phase_fast defaults to PhaseFastSection.

hold_penalty kept as deprecated field for hyperopt adapter compat
(Task 4 will clean it up).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

config/training/dqn-hyperopt.toml

@@ -61,6 +61,24 @@ gradient_accumulation_steps = [1, 1]   # fixed at 1 for now
 # IQN dual-head
 iqn_lambda = [0.0, 2.0]
 
+# Composite reward weights
+w_dsr = [0.1, 2.0]
+w_pnl = [0.0, 1.0]
+w_dd = [0.0, 5.0]
+w_idle = [0.0, 0.1]
+dd_threshold = [0.01, 0.10]
+loss_aversion = [1.0, 3.0]
+time_decay_rate = [0.0001, 0.005]
+
+[reward]
+w_dsr = 1.0
+w_pnl = 0.3
+w_dd = 1.0
+w_idle = 0.01
+dd_threshold = 0.02
+loss_aversion = 1.5
+time_decay_rate = 0.0005
+
 [fixed]
 use_branching = true                   # GPU pipeline requires branching
 use_double_dqn = true
@@ -84,3 +102,10 @@ num_atoms = 11
 branch_hidden_dim = 64
 dueling_hidden_dim = 128
 v_range = 20.0
+w_dsr = 1.0
+w_pnl = 0.3
+w_dd = 1.0
+w_idle = 0.01
+dd_threshold = 0.02
+loss_aversion = 1.5
+time_decay_rate = 0.0005

config/training/dqn-production.toml

@@ -63,4 +63,12 @@ min_loss_improvement_pct = 0.1
 [experience]
 initial_capital = 100000.0
 tx_cost_multiplier = 0.0001
-hold_reward = 0.001
+
+[reward]
+w_dsr = 1.0
+w_pnl = 0.3
+w_dd = 1.0
+w_idle = 0.01
+dd_threshold = 0.02
+loss_aversion = 1.5
+time_decay_rate = 0.0005

config/training/dqn-smoketest.toml

@@ -27,3 +27,12 @@ min_epochs_before_stopping = 5
 [experience]
 gpu_n_episodes = 16
 gpu_timesteps_per_episode = 50
+
+[reward]
+w_dsr = 1.0
+w_pnl = 0.3
+w_dd = 1.0
+w_idle = 0.01
+dd_threshold = 0.02
+loss_aversion = 1.5
+time_decay_rate = 0.0005