diff --git a/DQN_HYPEROPT_DRYRUN_INSTRUCTIONS.md b/DQN_HYPEROPT_DRYRUN_INSTRUCTIONS.md
new file mode 100644
index 000000000..8d9b9e1b1
--- /dev/null
+++ b/DQN_HYPEROPT_DRYRUN_INSTRUCTIONS.md
@@ -0,0 +1,241 @@
+# DQN Hyperopt Dry-Run Instructions
+
+**Created**: 2025-11-06 (Wave 12-A29)
+**Purpose**: Validate hyperopt setup before full 100-trial campaign
+**Location**: `/home/jgrusewski/Work/foxhunt/scripts/hyperopt_dqn_dryrun.sh`
+
+---
+
+## Quick Start
+
+```bash
+# Run the dry-run (5-10 minutes)
+./scripts/hyperopt_dqn_dryrun.sh
+```
+
+---
+
+## What It Does
+
+### 1. Configuration
+- **Trials**: 5 (fast validation)
+- **Epochs per trial**: 10 (enough to see convergence)
+- **Duration**: 5-10 minutes
+- **Cost**: $0.02-$0.04 (RTX A4000)
+
+### 2. Pre-Flight Checks
+- ✅ Verifies parquet file exists (`test_data/ES_FUT_180d.parquet`)
+- ✅ Checks CUDA availability
+- ✅ Displays GPU information
+
+### 3. Training Run
+- Executes `cargo run --release -p ml --example hyperopt_dqn_demo --features cuda`
+- Captures all logs to `/tmp/dqn_hyperopt_logs/dqn_hyperopt_dryrun_TIMESTAMP.log`
+- Displays output to console in real-time
+
+### 4. Validation Checks
+
+#### Critical Checks (must pass)
+1. **Training completed without errors**: No panics, crashes, or errors
+2. **Gradient clipping working**: No gradient explosions or Q-value divergence
+3. **Action distribution logged**: Monitoring is active
+4. **Gradient clipping enabled**: Config shows `gradient_clip_norm: Some(10.0)`
+
+#### Optional Checks (informational)
+5. **HOLD penalty weight**: Config shows `hold_penalty_weight: 0.01`
+6. **Portfolio tracking**: References to portfolio features found
+
+### 5. Results Summary
+- **Pass**: All 4 critical checks passed → Ready for full campaign
+- **Fail**: One or more critical checks failed → Review and fix issues
+
+---
+
+## Wave 11 Validations
+
+The dry-run verifies that all Wave 11 bug fixes are operational:
+
+| Bug # | Description | Validation Method |
+|-------|-------------|-------------------|
+| **#1** | Gradient clipping (max_norm=10.0) | No gradient explosions in logs |
+| **#2** | Portfolio tracking via PortfolioTracker | Portfolio feature references found |
+| **#3** | HOLD penalty (0.01 weight) | Config shows hold_penalty_weight |
+| **#4** | Close price extraction accuracy | No reward calculation errors |
+
+---
+
+## Expected Output
+
+### Success Case
+
+```
+======================================
+Overall Result: 4/4 critical checks passed
+======================================
+
+🎉 DRY-RUN PASSED
+
+✅ All critical validations passed
+✅ Wave 11 bug fixes appear operational
+✅ Ready for full hyperopt campaign
+
+Next Steps:
+  1. Review hyperopt results in logs: /tmp/dqn_hyperopt_logs/...
+  2. Verify action diversity is reasonable (not 100% HOLD)
+  3. Proceed with full 100-trial campaign
+```
+
+### Failure Case
+
+```
+======================================
+Overall Result: 2/4 critical checks passed
+======================================
+
+⚠️  DRY-RUN COMPLETED WITH WARNINGS
+
+❌ 2 critical checks failed
+⚠️  Review issues above before proceeding
+
+Troubleshooting:
+  1. Check logs: /tmp/dqn_hyperopt_logs/...
+  2. Look for specific error messages
+  3. Verify Wave 11 fixes are compiled correctly
+  4. Re-run dry-run after fixes
+```
+
+---
+
+## Logs Location
+
+All logs are saved to `/tmp/dqn_hyperopt_logs/` with timestamp:
+
+```
+/tmp/dqn_hyperopt_logs/dqn_hyperopt_dryrun_20251106_085230.log
+```
+
+Logs include:
+- Full training output
+- Hyperopt trial results
+- Action distribution statistics
+- Q-value monitoring
+- Gradient norms
+- Loss values
+
+---
+
+## Next Steps After Success
+
+### Full Hyperopt Campaign
+
+Once dry-run passes, proceed with full campaign:
+
+```bash
+cargo run --release -p ml --example hyperopt_dqn_demo --features cuda -- \
+  --parquet-file test_data/ES_FUT_180d.parquet \
+  --trials 100 \
+  --epochs 50
+```
+
+**Estimates**:
+- Duration: 60-90 minutes
+- Cost: $0.25-$0.38 (RTX A4000)
+- Expected: Best hyperparameters for production DQN
+
+### Deploy to Runpod (Optional)
+
+For faster execution with more powerful GPU:
+
+```bash
+python3 scripts/python/runpod/runpod_deploy.py \
+  --gpu-type "RTX A4000" \
+  --command "hyperopt_dqn_demo \
+    --parquet-file /runpod-volume/test_data/ES_FUT_180d.parquet \
+    --trials 100 --epochs 50"
+```
+
+---
+
+## Troubleshooting
+
+### Issue: 100% HOLD Actions
+
+**Symptom**: Action distribution shows `HOLD=100.0%`
+**Cause**: HOLD penalty not active or too weak
+**Fix**: Check `hold_penalty_weight` and `movement_threshold` in config
+
+### Issue: Gradient Explosions
+
+**Symptom**: "Q-VALUE DIVERGENCE" or "gradient explosion" in logs
+**Cause**: Gradient clipping disabled or too high
+**Fix**: Verify `gradient_clip_norm: Some(10.0)` in DQNHyperparameters
+
+### Issue: Portfolio Tracking Errors
+
+**Symptom**: Errors about missing portfolio features
+**Cause**: PortfolioTracker not initialized correctly
+**Fix**: Check DQNTrainer initialization with `feature_vector_to_state` parameter
+
+### Issue: Training Takes Too Long
+
+**Symptom**: Each trial takes >5 minutes
+**Cause**: CPU fallback or large dataset
+**Fix**: Verify CUDA is available with `nvidia-smi`
+
+---
+
+## Script Details
+
+### File Structure
+
+```bash
+scripts/
+└── hyperopt_dqn_dryrun.sh     # Main dry-run script (7.9KB)
+```
+
+### Script Sections
+
+1. **Configuration**: Trial/epoch counts, file paths
+2. **Banner**: Display run parameters
+3. **Pre-flight checks**: Validate environment
+4. **Run hyperopt**: Execute training with logging
+5. **Validation checks**: Parse logs for success/failure
+6. **Results summary**: Display pass/fail status
+
+### Exit Codes
+
+- `0`: All critical checks passed (success)
+- `1`: One or more critical checks failed (review needed)
+- `>1`: Script error (file not found, compilation failure, etc.)
+
+---
+
+## References
+
+- **CLAUDE.md**: Wave 11 DQN bug fix campaign
+- **hyperopt_dqn_demo.rs**: Hyperopt implementation (`ml/examples/hyperopt_dqn_demo.rs`)
+- **DQNHyperparameters**: Config struct (`ml/src/trainers/dqn.rs:48-79`)
+- **TrainingMonitor**: Action distribution tracking (`ml/src/trainers/dqn.rs:118-287`)
+
+---
+
+## Success Criteria
+
+✅ **PASS**: All 4 critical checks green
+✅ **PASS**: Action diversity >5% per action (not 100% HOLD)
+✅ **PASS**: No gradient explosions or Q-value divergence
+✅ **PASS**: Loss values reasonable (<10)
+
+**Result**: Ready for full 100-trial hyperopt campaign
+
+---
+
+## Wave 12-A29 Completion Summary
+
+- ✅ Script created: `scripts/hyperopt_dqn_dryrun.sh`
+- ✅ Script is executable: `chmod +x`
+- ✅ Script syntax valid: `bash -n` passed
+- ✅ Hyperopt example compiled: No errors
+- ✅ Documentation created: This file
+
+**Status**: Ready to run dry-run validation
diff --git a/WAVE12_A29_DRYRUN_QUICK_REF.txt b/WAVE12_A29_DRYRUN_QUICK_REF.txt
new file mode 100644
index 000000000..8252a95a1
--- /dev/null
+++ b/WAVE12_A29_DRYRUN_QUICK_REF.txt
@@ -0,0 +1,103 @@
+WAVE 12-A29: DQN HYPEROPT DRY-RUN SCRIPT - QUICK REFERENCE
+============================================================
+
+STATUS: ✅ COMPLETE (2025-11-06)
+
+SCRIPT LOCATION
+---------------
+/home/jgrusewski/Work/foxhunt/scripts/hyperopt_dqn_dryrun.sh
+
+USAGE
+-----
+./scripts/hyperopt_dqn_dryrun.sh
+
+CONFIGURATION
+-------------
+Trials:   5
+Epochs:   10 per trial
+Duration: 5-10 minutes
+Cost:     $0.02-$0.04 (RTX A4000)
+
+VALIDATION CHECKS (4 CRITICAL)
+-------------------------------
+1. Training completed without errors
+2. Gradient clipping working (no explosions)
+3. Action distribution logged
+4. Gradient clipping enabled in config
+
+WAVE 11 BUG FIX VALIDATIONS
+----------------------------
+Bug #1: Gradient clipping (max_norm=10.0) → No explosions
+Bug #2: Portfolio tracking operational → Features present
+Bug #3: HOLD penalty enabled (0.01) → Config shows weight
+Bug #4: Close price extraction → No errors
+
+SUCCESS CRITERIA
+----------------
+✅ 4/4 critical checks pass
+✅ Action diversity >5% per action (not 100% HOLD)
+✅ No gradient explosions or Q-value divergence
+✅ Loss values reasonable (<10)
+
+LOGS LOCATION
+-------------
+/tmp/dqn_hyperopt_logs/dqn_hyperopt_dryrun_TIMESTAMP.log
+
+NEXT STEPS (AFTER DRY-RUN PASSES)
+----------------------------------
+1. Review hyperopt results in logs
+2. Verify action diversity is reasonable
+3. Proceed with full 100-trial campaign:
+
+   cargo run --release -p ml --example hyperopt_dqn_demo --features cuda -- \
+     --parquet-file test_data/ES_FUT_180d.parquet \
+     --trials 100 --epochs 50
+
+   Duration: 60-90 min
+   Cost: $0.25-$0.38
+
+EXIT CODES
+----------
+0: All checks passed (success)
+1: One or more checks failed (review needed)
+>1: Script error
+
+TROUBLESHOOTING
+---------------
+100% HOLD:
+  → Check hold_penalty_weight and movement_threshold
+
+Gradient explosions:
+  → Verify gradient_clip_norm: Some(10.0)
+
+Portfolio errors:
+  → Check PortfolioTracker initialization
+
+Training too slow:
+  → Verify CUDA with nvidia-smi
+
+SCRIPT DETAILS
+--------------
+Size: 7.9KB
+Sections:
+  1. Configuration (trials, epochs, paths)
+  2. Pre-flight checks (files, CUDA)
+  3. Hyperopt execution (with logging)
+  4. Validation checks (4 critical + 2 optional)
+  5. Results summary (pass/fail report)
+
+DELIVERABLES
+------------
+✅ scripts/hyperopt_dqn_dryrun.sh (7.9KB, executable)
+✅ DQN_HYPEROPT_DRYRUN_INSTRUCTIONS.md (complete guide)
+✅ WAVE12_A29_DRYRUN_QUICK_REF.txt (this file)
+
+COMPILATION STATUS
+------------------
+✅ hyperopt_dqn_demo example compiled (1 warning, non-critical)
+✅ Script syntax validated (bash -n)
+✅ Script is executable (chmod +x)
+
+READY TO RUN
+------------
+./scripts/hyperopt_dqn_dryrun.sh
diff --git a/scripts/hyperopt_dqn_dryrun.sh b/scripts/hyperopt_dqn_dryrun.sh
new file mode 100755
index 000000000..a5d7ea6a7
--- /dev/null
+++ b/scripts/hyperopt_dqn_dryrun.sh
@@ -0,0 +1,253 @@
+#!/bin/bash
+#
+# DQN Hyperparameter Optimization Dry-Run Script
+#
+# Purpose: Quick validation of hyperopt setup before committing to full 100-trial campaign
+# Duration: 5-10 minutes
+# Cost: $0.02-$0.04 (RTX A4000)
+#
+# This script:
+# 1. Runs 5 hyperopt trials with 10 epochs each
+# 2. Captures all training logs (loss, action distribution, gradient norms)
+# 3. Validates that Wave 11 bug fixes are working correctly
+# 4. Provides pass/fail report with actionable next steps
+#
+# Usage:
+#   ./scripts/hyperopt_dqn_dryrun.sh
+
+set -e  # Exit on error
+set -o pipefail  # Exit if any command in pipeline fails
+
+# ==================== CONFIGURATION ====================
+
+TRIALS=5
+EPOCHS=10
+PARQUET_FILE="test_data/ES_FUT_180d.parquet"
+LOG_DIR="/tmp/dqn_hyperopt_logs"
+TIMESTAMP=$(date +%Y%m%d_%H%M%S)
+LOG_FILE="${LOG_DIR}/dqn_hyperopt_dryrun_${TIMESTAMP}.log"
+
+# Create log directory
+mkdir -p "$LOG_DIR"
+
+# ==================== BANNER ====================
+
+echo "========================================"
+echo "DQN Hyperopt Dry-Run"
+echo "========================================"
+echo "Configuration:"
+echo "  Trials: $TRIALS"
+echo "  Epochs per trial: $EPOCHS"
+echo "  Parquet file: $PARQUET_FILE"
+echo "  Log file: $LOG_FILE"
+echo ""
+echo "Expected duration: 5-10 minutes"
+echo "Expected cost: \$0.02-\$0.04 (RTX A4000)"
+echo ""
+echo "Wave 11 Validations:"
+echo "  ✓ Gradient clipping active (max_norm=10.0)"
+echo "  ✓ Portfolio tracking operational"
+echo "  ✓ HOLD penalty enabled (0.01 weight)"
+echo "  ✓ Close price extraction accurate"
+echo "========================================"
+echo ""
+
+# ==================== PRE-FLIGHT CHECKS ====================
+
+echo "[1/4] Pre-flight checks..."
+
+# Check if parquet file exists
+if [ ! -f "$PARQUET_FILE" ]; then
+    echo "❌ ERROR: Parquet file not found: $PARQUET_FILE"
+    exit 1
+fi
+echo "  ✓ Parquet file exists: $PARQUET_FILE"
+
+# Check if CUDA is available
+if command -v nvidia-smi &> /dev/null; then
+    echo "  ✓ CUDA available (nvidia-smi found)"
+    nvidia-smi --query-gpu=name,memory.total,memory.free --format=csv,noheader | head -1
+else
+    echo "  ⚠️  CUDA not available (will use CPU - slower)"
+fi
+
+echo ""
+
+# ==================== RUN HYPEROPT ====================
+
+echo "[2/4] Running hyperopt (this will take 5-10 minutes)..."
+echo ""
+
+# Run hyperopt and capture output to both file and stdout
+cargo run --release -p ml --example hyperopt_dqn_demo --features cuda -- \
+    --parquet-file "$PARQUET_FILE" \
+    --trials $TRIALS \
+    --epochs $EPOCHS \
+    2>&1 | tee "$LOG_FILE"
+
+EXIT_CODE=$?
+
+if [ $EXIT_CODE -ne 0 ]; then
+    echo ""
+    echo "❌ HYPEROPT FAILED (exit code: $EXIT_CODE)"
+    echo "   Check logs: $LOG_FILE"
+    exit $EXIT_CODE
+fi
+
+echo ""
+
+# ==================== VALIDATION CHECKS ====================
+
+echo "[3/4] Running validation checks..."
+echo ""
+
+# Check for errors/panics
+ERROR_COUNT=$(grep -i -c "error\|panic\|FAILED\|thread.*panicked" "$LOG_FILE" || true)
+echo "  Errors/panics: $ERROR_COUNT"
+
+# Check for gradient warnings (should be 0 with gradient clipping)
+GRAD_WARNINGS=$(grep -c "Large gradient\|gradient explosion\|Q-VALUE DIVERGENCE" "$LOG_FILE" || true)
+echo "  Gradient warnings: $GRAD_WARNINGS"
+
+# Check for Q-value explosions
+QVALUE_EXPLOSIONS=$(grep -c "Q-value explosion" "$LOG_FILE" || true)
+echo "  Q-value explosions: $QVALUE_EXPLOSIONS"
+
+# Check for action diversity (at least one trial should have varied actions)
+ACTION_DIST_COUNT=$(grep -c "Action Distribution" "$LOG_FILE" || true)
+echo "  Action distribution logs: $ACTION_DIST_COUNT"
+
+# Extract last trial's action distribution
+echo ""
+echo "  Last trial action distribution:"
+if grep -q "Action Distribution" "$LOG_FILE"; then
+    grep "Action Distribution" "$LOG_FILE" | tail -1 | sed 's/^/    /'
+else
+    echo "    ⚠️  No action distribution logs found"
+fi
+
+# Check for HOLD penalty usage (we use hold_penalty_weight in config)
+HOLD_PENALTY_CONFIG=$(grep -c "hold_penalty_weight: 0.01" "$LOG_FILE" || true)
+echo ""
+echo "  HOLD penalty weight in config: $HOLD_PENALTY_CONFIG occurrences"
+
+# Check for portfolio tracking (feature vector should include portfolio state)
+PORTFOLIO_FEATURES=$(grep -c "portfolio" "$LOG_FILE" || true)
+echo "  Portfolio tracking references: $PORTFOLIO_FEATURES"
+
+# Check for gradient clipping activation
+GRAD_CLIP_COUNT=$(grep -c "gradient_clip_norm: Some(10.0)" "$LOG_FILE" || true)
+echo "  Gradient clipping enabled: $GRAD_CLIP_COUNT occurrences"
+
+echo ""
+
+# ==================== RESULTS SUMMARY ====================
+
+echo "[4/4] Validation summary"
+echo "========================================"
+
+# Count passes and failures
+CHECKS_PASSED=0
+CHECKS_FAILED=0
+
+echo ""
+echo "Critical Checks:"
+echo "----------------"
+
+# Check 1: Training completed without errors
+if [ $ERROR_COUNT -eq 0 ]; then
+    echo "✅ Training completed without errors"
+    CHECKS_PASSED=$((CHECKS_PASSED + 1))
+else
+    echo "❌ Training had $ERROR_COUNT errors/panics"
+    CHECKS_FAILED=$((CHECKS_FAILED + 1))
+fi
+
+# Check 2: Gradient clipping working (no explosions)
+if [ $GRAD_WARNINGS -eq 0 ] && [ $QVALUE_EXPLOSIONS -eq 0 ]; then
+    echo "✅ Gradient clipping working (no explosions/warnings)"
+    CHECKS_PASSED=$((CHECKS_PASSED + 1))
+else
+    echo "❌ Gradient issues detected ($GRAD_WARNINGS warnings, $QVALUE_EXPLOSIONS explosions)"
+    CHECKS_FAILED=$((CHECKS_FAILED + 1))
+fi
+
+# Check 3: Action distribution logged
+if [ $ACTION_DIST_COUNT -gt 0 ]; then
+    echo "✅ Action distribution logged ($ACTION_DIST_COUNT times)"
+    CHECKS_PASSED=$((CHECKS_PASSED + 1))
+else
+    echo "❌ No action distribution logs found"
+    CHECKS_FAILED=$((CHECKS_FAILED + 1))
+fi
+
+# Check 4: Gradient clipping config present
+if [ $GRAD_CLIP_COUNT -gt 0 ]; then
+    echo "✅ Gradient clipping enabled in config"
+    CHECKS_PASSED=$((CHECKS_PASSED + 1))
+else
+    echo "⚠️  Gradient clipping config not found in logs"
+    CHECKS_FAILED=$((CHECKS_FAILED + 1))
+fi
+
+echo ""
+echo "Optional Checks:"
+echo "----------------"
+
+# Check 5: HOLD penalty weight configured
+if [ $HOLD_PENALTY_CONFIG -gt 0 ]; then
+    echo "✅ HOLD penalty weight configured (0.01)"
+else
+    echo "⚠️  HOLD penalty weight not found in logs (may still be working)"
+fi
+
+# Check 6: Portfolio tracking present
+if [ $PORTFOLIO_FEATURES -gt 0 ]; then
+    echo "✅ Portfolio tracking references found"
+else
+    echo "⚠️  Portfolio tracking references not found (may still be working)"
+fi
+
+echo ""
+echo "========================================"
+echo "Overall Result: $CHECKS_PASSED/4 critical checks passed"
+echo "========================================"
+echo ""
+
+# Final verdict
+if [ $CHECKS_FAILED -eq 0 ]; then
+    echo "🎉 DRY-RUN PASSED"
+    echo ""
+    echo "✅ All critical validations passed"
+    echo "✅ Wave 11 bug fixes appear operational"
+    echo "✅ Ready for full hyperopt campaign"
+    echo ""
+    echo "Next Steps:"
+    echo "  1. Review hyperopt results in logs: $LOG_FILE"
+    echo "  2. Verify action diversity is reasonable (not 100% HOLD)"
+    echo "  3. Proceed with full 100-trial campaign:"
+    echo "     cargo run --release -p ml --example hyperopt_dqn_demo --features cuda -- \\"
+    echo "       --parquet-file $PARQUET_FILE --trials 100 --epochs 50"
+    echo ""
+    echo "Estimated full campaign:"
+    echo "  Duration: 60-90 minutes"
+    echo "  Cost: \$0.25-\$0.38 (RTX A4000)"
+    exit 0
+else
+    echo "⚠️  DRY-RUN COMPLETED WITH WARNINGS"
+    echo ""
+    echo "❌ $CHECKS_FAILED critical checks failed"
+    echo "⚠️  Review issues above before proceeding"
+    echo ""
+    echo "Troubleshooting:"
+    echo "  1. Check logs: $LOG_FILE"
+    echo "  2. Look for specific error messages"
+    echo "  3. Verify Wave 11 fixes are compiled correctly"
+    echo "  4. Re-run dry-run after fixes"
+    echo ""
+    echo "Common Issues:"
+    echo "  - Gradient explosions: Check gradient_clip_norm in DQNHyperparameters"
+    echo "  - 100% HOLD: Check hold_penalty_weight and movement_threshold"
+    echo "  - Portfolio errors: Check PortfolioTracker initialization"
+    exit 1
+fi