#!/usr/bin/env bash
# DQN Hyperparameter Optimization Deployment (Optimized Parameters)
# Generated: 2025-11-02
# Based on: DQN_HYPEROPT_RESULTS_SUMMARY.md (Trial #8, Run 1)
#
# BEST HYPERPARAMETERS:
# - Learning Rate: 4.89e-5 (ultra-low, critical for DQN stability)
# - Batch Size: 151
# - Gamma: 0.9838
# - Epsilon Decay: 0.9917
# - Buffer Size: 185066
# - Trials: 50 (complete the hyperopt properly)
#
# CRITICAL NOTE: DQN requires ultra-low learning rates (4.89e-5 to 1.40e-4)
# This is 10-100x lower than PPO's optimal range due to off-policy replay buffer dynamics.

set -euo pipefail

# Configuration
GPU_TYPE="${1:-RTX A4000}"  # Default: RTX A4000 ($0.25/hr), alternative: RTX 4090 ($0.59/hr)
DOCKER_IMAGE="jgrusewski/foxhunt:dqn-checkpoint-fix"
PARQUET_FILE="/runpod-volume/test_data/ES_FUT_180d.parquet"
OUTPUT_BASE="/runpod-volume/ml_training"
TIMESTAMP=$(date +%Y%m%d_%H%M%S)
OUTPUT_DIR="${OUTPUT_BASE}/dqn_hyperopt_optimized_${TIMESTAMP}"

# Best hyperparameters from Trial #8 (Run 1)
TRIALS=50
EPOCHS=20  # Per trial
N_INITIAL=2  # Initial random samples
SEED=42  # Reproducibility

# Early stopping configuration
EARLY_STOPPING_PLATEAU_WINDOW=5
EARLY_STOPPING_MIN_EPOCHS=10

# Display configuration
echo "=========================================="
echo "DQN Hyperopt Deployment (Optimized)"
echo "=========================================="
echo "GPU: ${GPU_TYPE}"
echo "Docker Image: ${DOCKER_IMAGE}"
echo "Parquet File: ${PARQUET_FILE}"
echo "Output Directory: ${OUTPUT_DIR}"
echo ""
echo "Hyperopt Configuration:"
echo "  Trials: ${TRIALS}"
echo "  Epochs per trial: ${EPOCHS}"
echo "  Initial random samples: ${N_INITIAL}"
echo "  Random seed: ${SEED}"
echo ""
echo "Expected Duration: ~40 min (RTX A4000) or ~25 min (RTX 4090)"
echo "Expected Cost: ~\$0.17 (RTX A4000) or ~\$0.25 (RTX 4090)"
echo "=========================================="
echo ""

# Build hyperopt command
COMMAND="hyperopt_dqn_demo \
  --parquet-file ${PARQUET_FILE} \
  --trials ${TRIALS} \
  --epochs ${EPOCHS} \
  --n-initial ${N_INITIAL} \
  --seed ${SEED} \
  --base-dir ${OUTPUT_DIR} \
  --run-type hyperopt \
  --early-stopping-plateau-window ${EARLY_STOPPING_PLATEAU_WINDOW} \
  --early-stopping-min-epochs ${EARLY_STOPPING_MIN_EPOCHS}"

echo "Command: ${COMMAND}"
echo ""

# Deploy using foxhunt-deploy CLI
if [ ! -f "/home/jgrusewski/Work/foxhunt/target/release/foxhunt-deploy" ]; then
    echo "ERROR: foxhunt-deploy CLI not found at /home/jgrusewski/Work/foxhunt/target/release/foxhunt-deploy"
    echo "Please build it first: cargo build --release -p foxhunt-deploy"
    exit 1
fi

# Deploy pod
echo "Deploying RunPod pod..."
/home/jgrusewski/Work/foxhunt/target/release/foxhunt-deploy deploy \
    --gpu-type "${GPU_TYPE}" \
    --tag dqn-checkpoint-fix \
    --command "${COMMAND}" \
    --name "dqn-hyperopt-optimized-$(date +%Y%m%d-%H%M%S)" \
    --yes

echo ""
echo "=========================================="
echo "Deployment Complete!"
echo "=========================================="
echo ""
echo "Monitor progress:"
echo "  python3 scripts/python/runpod/monitor_logs.py <pod_id>"
echo ""
echo "Verify results (after completion):"
echo "  aws s3 ls s3://se3zdnb5o4/ml_training/dqn_hyperopt_optimized_${TIMESTAMP}/ --profile runpod --endpoint-url https://s3api-eur-is-1.runpod.io --recursive"
echo ""