feat(rl): tier 2 wave-scale — γ=0.995, PER 32k, min-hold 100

Prepared for next run after the γ=0.99 1M run completes:

- γ floor 0.99 → 0.995: horizon 100 → 200 steps (50 seconds).
  Real ES directional moves (2-5 points) happen at this scale.
- PER 16384 → 32768: 2048 unique steps of replay depth. Supports
  the 200-step γ horizon with margin.
- Min-hold 50 → 100 steps (25 seconds): commit to the full wave.
  Short-hold penalty threshold matches.

Safe to push because raw-reward re-normalization eliminates scale
drift in the deeper buffer, and the ±2% scale clamp keeps targets
stable across the 2048-step replay window.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

crates/ml-alpha/cuda/rl_gamma_controller.cu

@@ -45,7 +45,7 @@
 // the policy myopic).
 
 #define RL_GAMMA_INDEX   400
-#define GAMMA_MIN        0.99f
+#define GAMMA_MIN        0.995f
 #define GAMMA_MAX        0.999f
 #define WIENER_ALPHA_FLOOR 0.4f
 

crates/ml-alpha/examples/alpha_rl_train.rs

@@ -145,7 +145,7 @@ struct Cli {
 
     /// PER buffer capacity. At b_size=16, capacity/16 = unique steps
     /// retained. 32768/16 = 2048 steps of replay depth.
-    #[arg(long, default_value_t = 16384)]
+    #[arg(long, default_value_t = 32768)]
     per_capacity: usize,
 
     /// Random seed pinning RNG + Xavier init + ISV controller bootstrap

crates/ml-alpha/src/trainer/integrated.rs

@@ -294,7 +294,7 @@ impl Default for IntegratedTrainerConfig {
             perception: PerceptionTrainerConfig::default(),
             dqn_seed: 0xDA_DA_DA_DA,
             ppo_seed: 0xBE_BE_BE_BE,
-            per_capacity: 16384,
+            per_capacity: 32768,
             per_seed: 0x9E37_79B9_7F4A_7C15,
         }
     }
@@ -1652,10 +1652,10 @@ impl IntegratedTrainer {
                 (crate::rl::isv_slots::RL_GATE_FRD_MAX_INDEX,      0.50),
                 (crate::rl::isv_slots::RL_GATE_ADJUST_RATE_INDEX,  0.95),
                 (crate::rl::isv_slots::RL_ENTRY_COST_INDEX,        15.0),
-                (crate::rl::isv_slots::RL_SHORT_HOLD_MIN_STEPS_INDEX, 50.0),
+                (crate::rl::isv_slots::RL_SHORT_HOLD_MIN_STEPS_INDEX, 100.0),
                 (crate::rl::isv_slots::RL_SHORT_HOLD_PENALTY_INDEX,   0.5),
                 (crate::rl::isv_slots::RL_HOLD_BONUS_INDEX,          2.0),
-                (crate::rl::isv_slots::RL_MIN_HOLD_STEPS_INDEX,    50.0),
+                (crate::rl::isv_slots::RL_MIN_HOLD_STEPS_INDEX,    100.0),
                 (crate::rl::isv_slots::RL_MULTIRES_HORIZON_1_INDEX, 1.0),
                 (crate::rl::isv_slots::RL_MULTIRES_HORIZON_2_INDEX, 10.0),
                 (crate::rl::isv_slots::RL_MULTIRES_HORIZON_3_INDEX, 600.0),

infra/k8s/argo/alpha-rl-template.yaml

@@ -48,7 +48,7 @@ spec:
       - name: seq-len
         value: "32"
       - name: per-capacity
-        value: "16384"
+        value: "32768"
       - name: instrument-mode
         value: "all"
       - name: log-every