#!/bin/bash
set -e

echo "========================================="
echo "DQN Hyperopt Deployment (Fixed Reward Function)"
echo "========================================="
echo ""

# Set PYTHONPATH
export PYTHONPATH="/home/jgrusewski/Work/foxhunt:$PYTHONPATH"

# Activate venv
source .venv/bin/activate

# Deploy DQN hyperopt with fixed reward function
python3 scripts/runpod_deploy.py \
    --gpu-type "RTX A4000" \
    --image "jgrusewski/foxhunt-hyperopt:latest" \
    --command "hyperopt_dqn_demo --parquet-file /runpod-volume/test_data/ES_FUT_180d.parquet --trials 50 --epochs 100 --base-dir /runpod-volume/ml_training/dqn_hyperopt_fixed --early-stopping-min-epochs 50"

echo ""
echo "✅ DQN hyperopt deployment initiated"
echo "Monitor logs: python3 scripts/python/runpod/monitor_logs.py <pod_id>"
echo "Expected duration: 24-36 hours"
echo "Expected cost: \$6.00-\$9.00 @ \$0.25/hr (RTX A4000)"
echo ""
echo "Success Criteria:"
echo "  - Action distribution: 20-40% each (BUY/SELL/HOLD)"
echo "  - Reward std > 0.1 (no constant reward warnings)"
echo "  - Q-values balanced (divergence < 100)"
echo "  - Final backtest: > 10% return, Sharpe > 1.5"