COE379L_Project3/lev_PPO.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "57963548",
   "metadata": {},
   "source": [
    "# Improved PPO Training for Maglev Pod\n",
    "\n",
    "## Major Changes to Enable Learning:\n",
    "\n",
    "### 1. **Reward Function (lev_pod_env.py)**\n",
    "**Problem**: Squared penalties created rewards of -7000 to -8200, making learning impossible\n",
    "- `(gap_error * 100)²` could reach 10,000+ for small errors\n",
    "- +1.0 survival bonus was meaningless compared to penalties\n",
    "\n",
    "**Solution**: Exponential reward shaping with reasonable scales\n",
    "- Gap reward: `exp(-0.5 * (error/3mm)²)` → smooth 0 to 1.0 range\n",
    "- Small linear penalties for orientation (~0.02/degree)\n",
    "- Success bonus: +2.0 for excellent hovering (gap < 1mm, angles < 2°)\n",
    "- **New reward range: -10 to +3 per step** (was -8200 to +1 total)\n",
    "\n",
    "### 2. **Network Architecture**\n",
    "**Changes**:\n",
    "- Increased hidden units: 128 → 256\n",
    "- Added LayerNorm for training stability\n",
    "- Deeper shared layers (3 layers instead of 2)\n",
    "- Better initialization for exploration\n",
    "\n",
    "### 3. **Training Hyperparameters**\n",
    "**Changes**:\n",
    "- Policy LR: 3e-4 → 5e-4 (faster learning)\n",
    "- Value LR: 3e-4 → 1e-3 (even faster value updates)\n",
    "- Entropy coefficient: 0.01 → 0.02 (more exploration)\n",
    "- Added gradient clipping (max norm 0.5)\n",
    "- GAE lambda: 0.97 → 0.95 (less biased advantage estimates)\n",
    "- Episodes: 1000 → 2000\n",
    "\n",
    "### 4. **Termination Conditions**\n",
    "**Tightened for safety**:\n",
    "- Gap bounds: 2-40mm → 3-35mm\n",
    "- Angle tolerance: 20° → 15°\n",
    "- Failure penalty: -50 → -10 (scaled with new rewards)\n",
    "\n",
    "## Expected Behavior:\n",
    "- **Rewards should be positive or mildly negative** during good episodes\n",
    "- **Gap error should steadily decrease** from initial ~15mm toward target 16.49mm\n",
    "- **Episodes that reach 500 steps** indicate successful hovering\n",
    "- **Look for improvement over first 500 episodes**, then fine-tuning after"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "f28b2866",
   "metadata": {},
   "outputs": [],
   "source": [
    "import gymnasium as gym\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "import seaborn as sns\n",
    "import torch\n",
    "from torch import nn\n",
    "from torch import optim\n",
    "from torch.distributions import Normal\n",
    "from lev_pod_env import LevPodEnv"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "c49c95b6",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Torch Version: 2.8.0\n",
      "CUDA Available: True\n",
      "Using device: cuda\n"
     ]
    }
   ],
   "source": [
    "print(\"Torch Version:\", torch.__version__)\n",
    "print(\"CUDA Available:\", torch.cuda.is_available())\n",
    "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
    "print(\"Using device:\", device)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "70bb54d4",
   "metadata": {},
   "outputs": [],
   "source": [
    "class ActorCriticNetwork(nn.Module):\n",
    "    def __init__(self, state_dim, action_dim, hidden_dim=256):\n",
    "        super().__init__()\n",
    "        # Larger network with layer normalization for better learning\n",
    "        self.shared_layers = nn.Sequential(\n",
    "            nn.Linear(state_dim, hidden_dim),\n",
    "            nn.LayerNorm(hidden_dim),\n",
    "            nn.ReLU(),\n",
    "            nn.Linear(hidden_dim, hidden_dim),\n",
    "            nn.LayerNorm(hidden_dim),\n",
    "            nn.ReLU(),\n",
    "            nn.Linear(hidden_dim, hidden_dim // 2),\n",
    "            nn.ReLU()\n",
    "        )\n",
    "        # Policy outputs mean and log_std for continuous actions\n",
    "        self.policy_mean = nn.Sequential(\n",
    "            nn.Linear(hidden_dim // 2, hidden_dim // 2),\n",
    "            nn.ReLU(),\n",
    "            nn.Linear(hidden_dim // 2, action_dim),\n",
    "            nn.Tanh()  # Constrain to [-1, 1] range\n",
    "        )\n",
    "        # Initialize log_std to encourage exploration initially\n",
    "        self.policy_log_std = nn.Parameter(torch.ones(action_dim) * -0.5)\n",
    "        \n",
    "        self.value_layers = nn.Sequential(\n",
    "            nn.Linear(hidden_dim // 2, hidden_dim // 2),\n",
    "            nn.ReLU(),\n",
    "            nn.Linear(hidden_dim // 2, 1),\n",
    "        )\n",
    "\n",
    "    def value(self, observation):\n",
    "        shared_output = self.shared_layers(observation)\n",
    "        state_value = self.value_layers(shared_output)\n",
    "        return state_value\n",
    "    \n",
    "    def policy(self, observation):\n",
    "        shared_output = self.shared_layers(observation)\n",
    "        mean = self.policy_mean(shared_output)\n",
    "        std = torch.exp(self.policy_log_std)\n",
    "        return mean, std\n",
    "    \n",
    "    def forward(self, state):\n",
    "        shared_output = self.shared_layers(state)\n",
    "        mean = self.policy_mean(shared_output)\n",
    "        std = torch.exp(self.policy_log_std)\n",
    "        state_value = self.value_layers(shared_output)\n",
    "        return mean, std, state_value"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "2ed37deb",
   "metadata": {},
   "outputs": [],
   "source": [
    "class PPOTrainer():\n",
    "    def __init__(self, actor_critic, ppo_clip_val=0.2, target_kl_div=0.02,\n",
    "                  max_policy_train_iters=40, value_train_iters=40, policy_lr=5e-4, value_lr=1e-3, \n",
    "                  entropy_coef=0.02):\n",
    "        self.ac = actor_critic\n",
    "        self.ppo_clip_val = ppo_clip_val\n",
    "        self.target_kl_div = target_kl_div\n",
    "        self.max_policy_train_iters = max_policy_train_iters\n",
    "        self.value_train_iters = value_train_iters\n",
    "        self.entropy_coef = entropy_coef\n",
    "\n",
    "        policy_params = list(self.ac.shared_layers.parameters()) + \\\n",
    "                       list(self.ac.policy_mean.parameters()) + \\\n",
    "                       [self.ac.policy_log_std]\n",
    "        self.policy_optimizer = optim.Adam(policy_params, lr=policy_lr)\n",
    "\n",
    "        value_params = list(self.ac.shared_layers.parameters()) + \\\n",
    "                      list(self.ac.value_layers.parameters())\n",
    "        self.value_optimizer = optim.Adam(value_params, lr=value_lr)\n",
    "\n",
    "    def train_policy(self, obs, acts, old_log_probs, gaes):\n",
    "        for _ in range(self.max_policy_train_iters):\n",
    "            self.policy_optimizer.zero_grad()\n",
    "\n",
    "            new_mean, new_std = self.ac.policy(obs)\n",
    "            new_dist = Normal(new_mean, new_std)\n",
    "            new_log_probs = new_dist.log_prob(acts).sum(dim=-1)\n",
    "\n",
    "            policy_ratio = torch.exp(new_log_probs - old_log_probs)\n",
    "            clipped_ratio = policy_ratio.clamp(1 - self.ppo_clip_val, 1 + self.ppo_clip_val)\n",
    "\n",
    "            clipped_loss = clipped_ratio * gaes\n",
    "            unclipped_loss = policy_ratio * gaes\n",
    "\n",
    "            policy_loss = -torch.min(clipped_loss, unclipped_loss).mean()\n",
    "            \n",
    "            # Increased entropy bonus to encourage more exploration\n",
    "            entropy = new_dist.entropy().mean()\n",
    "            policy_loss = policy_loss - self.entropy_coef * entropy\n",
    "\n",
    "            policy_loss.backward()\n",
    "            # Gradient clipping for stability\n",
    "            torch.nn.utils.clip_grad_norm_(self.policy_optimizer.param_groups[0]['params'], 0.5)\n",
    "            self.policy_optimizer.step()\n",
    "\n",
    "            kl_div = (old_log_probs - new_log_probs).mean()\n",
    "            if kl_div > self.target_kl_div:\n",
    "                break\n",
    "          \n",
    "    def train_value(self, obs, returns):\n",
    "        for _ in range(self.value_train_iters):\n",
    "            self.value_optimizer.zero_grad()\n",
    "\n",
    "            values = self.ac.value(obs)\n",
    "            value_loss = (returns - values).pow(2).mean()\n",
    "            \n",
    "            value_loss.backward()\n",
    "            # Gradient clipping for stability\n",
    "            torch.nn.utils.clip_grad_norm_(self.value_optimizer.param_groups[0]['params'], 0.5)\n",
    "            self.value_optimizer.step()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "6f4f9f4b",
   "metadata": {},
   "outputs": [],
   "source": [
    "def discount_rewards(rewards, gamma=0.99):\n",
    "    discounted = np.zeros_like(rewards, dtype=np.float32)\n",
    "    running_add = 0\n",
    "    for t in reversed(range(len(rewards))):\n",
    "        running_add = running_add * gamma + rewards[t]\n",
    "        discounted[t] = running_add\n",
    "    return discounted\n",
    "\n",
    "def calculate_gaes(rewards, values, gamma=0.99, lam=0.95):\n",
    "    # Add 0 for terminal state bootstrap value\n",
    "    next_values = np.concatenate([values[1:], [0]])\n",
    "    deltas = rewards + gamma * next_values - values\n",
    "    gaes = discount_rewards(deltas, gamma * lam)\n",
    "    return gaes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "d7b17705",
   "metadata": {},
   "outputs": [],
   "source": [
    "def rollout(model, env, max_steps=500):  \n",
    "    train_data = [[],[],[],[],[]]  # obs, actions, rewards, values, log_probs\n",
    "    gap_heights = []  # Track gap heights during episode\n",
    "    obs, _ = env.reset()  # Gymnasium returns (obs, info)\n",
    "    \n",
    "    ep_reward = 0\n",
    "    for _ in range(max_steps):\n",
    "        with torch.no_grad():  # No gradients needed during rollout\n",
    "            mean, std, val = model(torch.tensor([obs], dtype=torch.float32, device=device))\n",
    "\n",
    "        # Sample continuous action from Normal distribution\n",
    "        act_distribution = Normal(mean, std)\n",
    "        act = act_distribution.sample()\n",
    "        act_log_prob = act_distribution.log_prob(act).sum(dim=-1)\n",
    "        \n",
    "        # Convert to numpy array for environment\n",
    "        act_np = act.squeeze(0).cpu().numpy()\n",
    "        next_obs, reward, terminated, truncated, _ = env.step(act_np)\n",
    "        \n",
    "        # Extract gap heights from observation (first 4 values are normalized gaps)\n",
    "        # Denormalize gaps: multiply by gap_scale (0.015m = 15mm)\n",
    "        gap_heights.append(obs[:4] * env.gap_scale * 1000)  # Convert to mm\n",
    "\n",
    "        # Store as Python scalars (moving to CPU only when necessary)\n",
    "        for i, item in enumerate([obs, act_np, reward, val.item(), act_log_prob.item()]):\n",
    "            train_data[i].append(item)\n",
    "        \n",
    "        obs = next_obs\n",
    "        ep_reward += reward\n",
    "        done = terminated or truncated\n",
    "\n",
    "        if done:\n",
    "            break\n",
    "        \n",
    "    train_data = [np.array(x, dtype=np.float32) for x in train_data]\n",
    "    train_data[3] = calculate_gaes(rewards=train_data[2], values=train_data[3])\n",
    "    \n",
    "    # Calculate average gap height error\n",
    "    gap_heights = np.array(gap_heights)  # Shape: (steps, 4 sensors)\n",
    "    avg_gap_per_step = gap_heights.mean(axis=1)  # Average across 4 sensors\n",
    "    target_gap_mm = 16.491741\n",
    "    avg_gap_error = np.abs(avg_gap_per_step - target_gap_mm).mean()\n",
    "\n",
    "    return train_data, ep_reward, avg_gap_error"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7ee8fb34",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Loading maglev model from maglev_model.pkl...\n",
      "Model loaded. Degree: 6\n",
      "Force R2: 1.0000\n",
      "Torque R2: 0.9999\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\pulip\\AppData\\Local\\Temp\\ipykernel_32220\\3744901434.py:9: UserWarning: Creating a tensor from a list of numpy.ndarrays is extremely slow. Please consider converting the list to a single numpy.ndarray with numpy.array() before converting to a tensor. (Triggered internally at C:\\bld\\libtorch_1762089177580\\work\\torch\\csrc\\utils\\tensor_new.cpp:256.)\n",
      "  mean, std, val = model(torch.tensor([obs], dtype=torch.float32, device=device))\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Reward: 1990.308654679309\n",
      "Episode length: 500\n",
      "Reward per step: 3.980617309358618\n",
      "Average gap error: 19.005 mm\n",
      "\n",
      "Theoretical Maximum:\n",
      "  Best per step: 3.00\n",
      "  Realistic good per step: 0.80\n",
      "  Best total (500 steps): 1500\n",
      "  Current % of realistic: 497.6%\n"
     ]
    }
   ],
   "source": [
    "# The following was generated by AI - see [19]\n",
    "environ = LevPodEnv(use_gui=False, initial_gap_mm=14, max_steps=500)  # Start below target\n",
    "model = ActorCriticNetwork(environ.observation_space.shape[0], environ.action_space.shape[0]).to(device)\n",
    "train_data, reward, gap_error = rollout(model, environ)\n",
    "print(\"Reward:\", reward)\n",
    "print(\"Episode length:\", len(train_data[0]))\n",
    "print(\"Reward per step:\", reward / len(train_data[0]))\n",
    "print(f\"Average gap error: {gap_error:.3f} mm\")\n",
    "\n",
    "# Calculate theoretical maximum reward for reference (NEW REWARD STRUCTURE)\n",
    "max_steps = 500\n",
    "# Best case: gap_reward=1.0, no penalties, success_bonus=2.0\n",
    "theoretical_max_per_step = 3.0  # 1.0 (gap) + 2.0 (success bonus) + 0 (no penalties)\n",
    "# Realistic good case: gap_reward~0.9, small penalties\n",
    "realistic_good_per_step = 0.8\n",
    "theoretical_max_total = theoretical_max_per_step * max_steps\n",
    "realistic_good_total = realistic_good_per_step * max_steps\n",
    "\n",
    "print(f\"\\nTheoretical Maximum:\")\n",
    "print(f\"  Best per step: {theoretical_max_per_step:.2f}\")\n",
    "print(f\"  Realistic good per step: {realistic_good_per_step:.2f}\")\n",
    "print(f\"  Best total (500 steps): {theoretical_max_total:.0f}\")\n",
    "print(f\"  Current % of realistic: {(reward/realistic_good_total)*100:.1f}%\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1b8b1ca2",
   "metadata": {},
   "source": [
    "## Key Improvements Made:\n",
    "\n",
    "1. **Better Reward Scaling**: Changed from squared penalties (up to 10,000+) to exponential rewards (~0 to 1) with smaller linear penalties\n",
    "2. **Larger Network**: Increased from 128 to 256 hidden units with LayerNorm for better learning capacity\n",
    "3. **More Exploration**: Increased entropy coefficient from 0.01 to 0.02, initialized log_std higher\n",
    "4. **Gradient Clipping**: Added to prevent exploding gradients\n",
    "5. **Higher Learning Rates**: Increased policy LR to 5e-4 and value LR to 1e-3\n",
    "6. **Tighter Termination**: Reduced angle tolerance to 15° and gap bounds to 3-35mm\n",
    "7. **Success Bonus**: Added +2.0 reward for excellent hovering (gap < 1mm, angles < 2°)\n",
    "\n",
    "Expected improvements:\n",
    "- Rewards should now be in range [-10, +3] instead of [-8000, +1]\n",
    "- Model should learn meaningful distinctions between good and bad states\n",
    "- Training should show steady improvement in gap error over episodes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e6f27ed4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Reward examples at different gap errors:\n",
      "   0mm error → 1.0000 reward\n",
      "   1mm error → 0.9460 reward\n",
      "   3mm error → 0.6065 reward\n",
      "   5mm error → 0.2494 reward\n",
      "  10mm error → 0.0039 reward\n",
      "  15mm error → 0.0000 reward\n",
      "\n",
      "Compare to old reward: (error*100)² would be:\n",
      "   1mm error → -10,000 penalty\n",
      "   3mm error → -90,000 penalty\n",
      "   5mm error → -250,000 penalty\n",
      "  10mm error → -1,000,000 penalty\n"
     ]
    }
   ],
   "source": [
    "# The following was generated by AI - see [20]\n",
    "# Visualize the new reward function\n",
    "gap_errors_mm = np.linspace(0, 20, 100)\n",
    "gap_rewards = np.exp(-0.5 * (gap_errors_mm / 3.0)**2)\n",
    "\n",
    "plt.figure(figsize=(10, 6))\n",
    "plt.plot(gap_errors_mm, gap_rewards, linewidth=2)\n",
    "plt.axvline(x=1.0, color='g', linestyle='--', label='Success bonus threshold (1mm)')\n",
    "plt.axvline(x=3.0, color='orange', linestyle='--', label='1 std dev (3mm)')\n",
    "plt.xlabel('Gap Error (mm)', fontsize=12)\n",
    "plt.ylabel('Gap Reward Component', fontsize=12)\n",
    "plt.title('New Reward Function: Smooth Exponential Decay', fontsize=14, fontweight='bold')\n",
    "plt.grid(True, alpha=0.3)\n",
    "plt.legend()\n",
    "plt.tight_layout()\n",
    "plt.show()\n",
    "\n",
    "print(\"Reward examples at different gap errors:\")\n",
    "for err in [0, 1, 3, 5, 10, 15]:\n",
    "    reward = np.exp(-0.5 * (err / 3.0)**2)\n",
    "    print(f\"  {err:2d}mm error → {reward:.4f} reward\")\n",
    "print(\"\\nCompare to old reward: (error*100)² would be:\")\n",
    "for err in [1, 3, 5, 10]:\n",
    "    old_penalty = (err * 100)**2\n",
    "    print(f\"  {err:2d}mm error → -{old_penalty:,} penalty\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "fb554183",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Logging to: RL_Trials/training_log_20251211_191801.txt\n",
      "Plot will be saved to: RL_Trials/gap_error_plot_20251211_191801.png\n"
     ]
    }
   ],
   "source": [
    "# The following was generated by AI - see [21]\n",
    "import os\n",
    "from datetime import datetime\n",
    "\n",
    "# Create RL_Trials folder if it doesn't exist\n",
    "os.makedirs('RL_Trials', exist_ok=True)\n",
    "\n",
    "# Create timestamped log file\n",
    "timestamp = datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n",
    "log_file_path = f'RL_Trials/training_log_{timestamp}.txt'\n",
    "plot_file_path = f'RL_Trials/gap_error_plot_{timestamp}.png'\n",
    "\n",
    "# Define training params\n",
    "num_episodes = 2000  # Increased for more learning time\n",
    "print_freq = 20  # Print less frequently\n",
    "gui_freq = 100  # Show GUI every 100 episodes\n",
    "\n",
    "# Create PPO trainer with improved hyperparameters\n",
    "ppo = PPOTrainer(\n",
    "    model, \n",
    "    policy_lr=5e-4,          # Higher learning rate\n",
    "    value_lr=1e-3,           # Even higher for value function\n",
    "    target_kl_div=0.02,      # Allow more policy updates\n",
    "    max_policy_train_iters=40,\n",
    "    value_train_iters=40,\n",
    "    entropy_coef=0.02        # More exploration\n",
    ")\n",
    "\n",
    "# Open log file\n",
    "log_file = open(log_file_path, 'w')\n",
    "log_file.write(f\"Training Started: {timestamp}\\n\")\n",
    "log_file.write(f\"Number of Episodes: {num_episodes}\\n\")\n",
    "log_file.write(f\"Print Frequency: {print_freq}\\n\")\n",
    "log_file.write(f\"Target Gap Height: {16.491741} mm\\n\")\n",
    "log_file.write(f\"Network: 256 hidden units with LayerNorm\\n\")\n",
    "log_file.write(f\"Policy LR: 5e-4, Value LR: 1e-3, Entropy: 0.02\\n\")\n",
    "log_file.write(\"=\"*70 + \"\\n\\n\")\n",
    "log_file.flush()\n",
    "\n",
    "print(f\"Logging to: {log_file_path}\")\n",
    "print(f\"Plot will be saved to: {plot_file_path}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "64994dcf",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Loading maglev model from maglev_model.pkl...\n",
      "Model loaded. Degree: 6\n",
      "Force R2: 1.0000\n",
      "Torque R2: 0.9999\n"
     ]
    }
   ],
   "source": [
    "environ = LevPodEnv(use_gui=True, initial_gap_mm=14, max_steps=500)  # Start below target"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "c3353cf5",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Ep   20 | R:  755.5 | Len: 204 | R/s:  3.70 (462.3%) | Gap: 16.74mm (min:14.73) | Best: 14.73mm\n",
      "Ep   40 | R:  407.2 | Len: 116 | R/s:  3.52 (439.9%) | Gap: 15.56mm (min:13.80) | Best: 13.80mm\n",
      "Ep   60 | R:  157.4 | Len:  57 | R/s:  2.78 (347.5%) | Gap: 14.87mm (min:13.91) | Best: 13.80mm\n",
      "Ep   80 | R:  182.7 | Len:  61 | R/s:  2.98 (372.0%) | Gap: 15.06mm (min:14.21) | Best: 13.80mm\n",
      "Ep  100 | R:  487.2 | Len: 134 | R/s:  3.65 (455.9%) | Gap: 16.10mm (min:14.31) | Best: 13.80mm\n",
      "Ep  120 | R: 1113.1 | Len: 297 | R/s:  3.75 (468.3%) | Gap: 17.64mm (min:15.95) | Best: 13.80mm\n",
      "Ep  140 | R: 1434.7 | Len: 385 | R/s:  3.72 (465.6%) | Gap: 18.21mm (min:16.13) | Best: 13.80mm\n",
      "Ep  160 | R:  641.4 | Len: 172 | R/s:  3.72 (464.8%) | Gap: 16.69mm (min:15.38) | Best: 13.80mm\n",
      "Ep  180 | R: 1029.0 | Len: 274 | R/s:  3.76 (469.7%) | Gap: 17.43mm (min:14.60) | Best: 13.80mm\n",
      "Ep  200 | R:  287.0 | Len:  85 | R/s:  3.39 (424.0%) | Gap: 15.61mm (min:14.18) | Best: 13.80mm\n",
      "Ep  220 | R:  330.9 | Len:  94 | R/s:  3.52 (440.4%) | Gap: 15.85mm (min:14.93) | Best: 13.80mm\n",
      "Ep  240 | R:  336.4 | Len: 103 | R/s:  3.28 (409.7%) | Gap: 15.15mm (min:13.83) | Best: 13.80mm\n",
      "Ep  260 | R:  128.2 | Len:  50 | R/s:  2.58 (321.9%) | Gap: 14.51mm (min:13.90) | Best: 13.80mm\n",
      "Ep  280 | R:  116.0 | Len:  46 | R/s:  2.51 (313.3%) | Gap: 14.30mm (min:13.49) | Best: 13.49mm\n",
      "Ep  300 | R:   95.0 | Len:  39 | R/s:  2.45 (306.0%) | Gap: 13.85mm (min:13.19) | Best: 13.19mm\n",
      "Ep  320 | R:  772.1 | Len: 200 | R/s:  3.86 (482.9%) | Gap: 16.77mm (min:15.05) | Best: 13.19mm\n",
      "Ep  340 | R:  152.7 | Len:  54 | R/s:  2.84 (354.5%) | Gap: 14.81mm (min:13.96) | Best: 13.19mm\n",
      "Ep  360 | R:  118.1 | Len:  47 | R/s:  2.52 (315.6%) | Gap: 14.36mm (min:13.50) | Best: 13.19mm\n",
      "Ep  380 | R:  290.8 | Len:  81 | R/s:  3.60 (450.2%) | Gap: 15.56mm (min:14.06) | Best: 13.19mm\n",
      "Ep  400 | R:  230.0 | Len:  69 | R/s:  3.35 (418.5%) | Gap: 15.38mm (min:14.74) | Best: 13.19mm\n",
      "Ep  420 | R:  305.9 | Len:  85 | R/s:  3.58 (447.5%) | Gap: 15.82mm (min:15.08) | Best: 13.19mm\n",
      "Ep  440 | R:  450.6 | Len: 116 | R/s:  3.90 (487.0%) | Gap: 16.25mm (min:14.81) | Best: 13.19mm\n",
      "Ep  460 | R:  624.2 | Len: 161 | R/s:  3.89 (486.0%) | Gap: 16.65mm (min:15.01) | Best: 13.19mm\n",
      "Ep  480 | R:  710.6 | Len: 192 | R/s:  3.70 (462.6%) | Gap: 16.62mm (min:14.71) | Best: 13.19mm\n",
      "Ep  500 | R:  131.1 | Len:  49 | R/s:  2.65 (331.8%) | Gap: 14.44mm (min:13.45) | Best: 13.19mm\n",
      "Ep  520 | R:  169.4 | Len:  58 | R/s:  2.90 (362.5%) | Gap: 14.97mm (min:14.22) | Best: 13.19mm\n",
      "Ep  540 | R:  929.9 | Len: 263 | R/s:  3.53 (441.4%) | Gap: 16.99mm (min:14.49) | Best: 13.19mm\n",
      "Ep  560 | R: 1760.6 | Len: 500 | R/s:  3.52 (440.1%) | Gap: 19.00mm (min:19.00) | Best: 13.19mm\n",
      "Ep  580 | R: 1763.0 | Len: 500 | R/s:  3.53 (440.7%) | Gap: 19.00mm (min:18.99) | Best: 13.19mm\n",
      "Ep  600 | R: 1775.4 | Len: 500 | R/s:  3.55 (443.8%) | Gap: 18.99mm (min:18.91) | Best: 13.19mm\n",
      "Ep  620 | R: 1298.7 | Len: 355 | R/s:  3.66 (457.5%) | Gap: 17.94mm (min:14.49) | Best: 13.19mm\n",
      "Ep  640 | R: 1576.3 | Len: 438 | R/s:  3.60 (450.3%) | Gap: 18.63mm (min:16.35) | Best: 13.19mm\n",
      "Ep  660 | R: 1762.6 | Len: 500 | R/s:  3.53 (440.7%) | Gap: 19.00mm (min:19.00) | Best: 13.19mm\n",
      "Ep  680 | R: 1761.3 | Len: 500 | R/s:  3.52 (440.3%) | Gap: 19.00mm (min:18.99) | Best: 13.19mm\n",
      "Ep  700 | R: 1761.0 | Len: 500 | R/s:  3.52 (440.2%) | Gap: 19.00mm (min:18.99) | Best: 13.19mm\n",
      "Ep  720 | R: 1754.8 | Len: 500 | R/s:  3.51 (438.7%) | Gap: 19.00mm (min:18.99) | Best: 13.19mm\n",
      "Ep  740 | R: 1755.3 | Len: 500 | R/s:  3.51 (438.8%) | Gap: 19.00mm (min:18.99) | Best: 13.19mm\n",
      "Ep  760 | R: 1756.6 | Len: 500 | R/s:  3.51 (439.2%) | Gap: 19.00mm (min:18.99) | Best: 13.19mm\n",
      "Ep  780 | R: 1759.2 | Len: 500 | R/s:  3.52 (439.8%) | Gap: 19.00mm (min:18.99) | Best: 13.19mm\n",
      "Ep  800 | R: 1756.9 | Len: 500 | R/s:  3.51 (439.2%) | Gap: 19.00mm (min:18.99) | Best: 13.19mm\n",
      "Ep  820 | R: 1759.2 | Len: 500 | R/s:  3.52 (439.8%) | Gap: 19.00mm (min:18.99) | Best: 13.19mm\n",
      "Ep  840 | R: 1593.2 | Len: 436 | R/s:  3.65 (456.7%) | Gap: 18.62mm (min:16.57) | Best: 13.19mm\n",
      "Ep  860 | R: 1209.1 | Len: 334 | R/s:  3.62 (452.2%) | Gap: 17.92mm (min:15.21) | Best: 13.19mm\n",
      "Ep  880 | R:  509.8 | Len: 149 | R/s:  3.43 (429.0%) | Gap: 16.16mm (min:14.21) | Best: 13.19mm\n",
      "Ep  900 | R:  496.0 | Len: 148 | R/s:  3.36 (419.9%) | Gap: 15.86mm (min:14.56) | Best: 13.19mm\n",
      "Ep  920 | R: 1770.0 | Len: 500 | R/s:  3.54 (442.5%) | Gap: 18.99mm (min:18.97) | Best: 13.19mm\n",
      "Ep  940 | R: 1763.3 | Len: 500 | R/s:  3.53 (440.8%) | Gap: 19.00mm (min:18.99) | Best: 13.19mm\n",
      "Ep  960 | R: 1753.9 | Len: 500 | R/s:  3.51 (438.5%) | Gap: 19.00mm (min:18.99) | Best: 13.19mm\n",
      "Ep  980 | R: 1751.9 | Len: 500 | R/s:  3.50 (438.0%) | Gap: 19.00mm (min:18.99) | Best: 13.19mm\n",
      "Ep 1000 | R: 1756.6 | Len: 500 | R/s:  3.51 (439.1%) | Gap: 19.00mm (min:18.99) | Best: 13.19mm\n",
      "Ep 1020 | R: 1754.6 | Len: 500 | R/s:  3.51 (438.7%) | Gap: 19.00mm (min:18.99) | Best: 13.19mm\n",
      "Ep 1040 | R: 1759.2 | Len: 500 | R/s:  3.52 (439.8%) | Gap: 19.00mm (min:19.00) | Best: 13.19mm\n",
      "Ep 1060 | R: 1756.7 | Len: 500 | R/s:  3.51 (439.2%) | Gap: 19.00mm (min:19.00) | Best: 13.19mm\n",
      "Ep 1080 | R: 1758.8 | Len: 500 | R/s:  3.52 (439.7%) | Gap: 19.00mm (min:18.99) | Best: 13.19mm\n",
      "Ep 1100 | R: 1756.2 | Len: 500 | R/s:  3.51 (439.1%) | Gap: 19.00mm (min:18.99) | Best: 13.19mm\n",
      "Ep 1120 | R: 1756.5 | Len: 500 | R/s:  3.51 (439.1%) | Gap: 19.00mm (min:18.99) | Best: 13.19mm\n",
      "Ep 1140 | R: 1760.5 | Len: 500 | R/s:  3.52 (440.1%) | Gap: 19.00mm (min:18.99) | Best: 13.19mm\n",
      "Ep 1160 | R: 1760.5 | Len: 500 | R/s:  3.52 (440.1%) | Gap: 19.00mm (min:19.00) | Best: 13.19mm\n",
      "Ep 1180 | R: 1756.5 | Len: 500 | R/s:  3.51 (439.1%) | Gap: 19.00mm (min:18.99) | Best: 13.19mm\n",
      "Ep 1200 | R: 1760.0 | Len: 500 | R/s:  3.52 (440.0%) | Gap: 19.00mm (min:19.00) | Best: 13.19mm\n",
      "Ep 1220 | R: 1758.7 | Len: 500 | R/s:  3.52 (439.7%) | Gap: 19.00mm (min:19.00) | Best: 13.19mm\n",
      "Ep 1240 | R: 1760.4 | Len: 500 | R/s:  3.52 (440.1%) | Gap: 19.00mm (min:19.00) | Best: 13.19mm\n",
      "Ep 1260 | R: 1753.5 | Len: 500 | R/s:  3.51 (438.4%) | Gap: 19.00mm (min:19.00) | Best: 13.19mm\n",
      "Ep 1280 | R: 1753.9 | Len: 500 | R/s:  3.51 (438.5%) | Gap: 19.00mm (min:19.00) | Best: 13.19mm\n",
      "Ep 1300 | R: 1758.0 | Len: 500 | R/s:  3.52 (439.5%) | Gap: 19.00mm (min:19.00) | Best: 13.19mm\n",
      "Ep 1320 | R: 1762.7 | Len: 500 | R/s:  3.53 (440.7%) | Gap: 19.00mm (min:19.00) | Best: 13.19mm\n",
      "Ep 1340 | R: 1693.0 | Len: 459 | R/s:  3.69 (460.9%) | Gap: 18.61mm (min:16.25) | Best: 13.19mm\n",
      "Ep 1360 | R:  713.0 | Len: 181 | R/s:  3.94 (492.2%) | Gap: 16.38mm (min:15.05) | Best: 13.19mm\n",
      "Ep 1380 | R: 2118.4 | Len: 486 | R/s:  4.36 (545.4%) | Gap: 18.38mm (min:17.32) | Best: 13.19mm\n",
      "Ep 1400 | R: 2157.4 | Len: 495 | R/s:  4.36 (544.9%) | Gap: 18.50mm (min:18.01) | Best: 13.19mm\n",
      "Ep 1420 | R: 1181.5 | Len: 262 | R/s:  4.50 (563.0%) | Gap: 16.90mm (min:15.79) | Best: 13.19mm\n",
      "Ep 1440 | R: 1332.5 | Len: 298 | R/s:  4.46 (558.1%) | Gap: 17.08mm (min:15.65) | Best: 13.19mm\n",
      "Ep 1460 | R: 1496.5 | Len: 332 | R/s:  4.51 (563.8%) | Gap: 17.27mm (min:15.62) | Best: 13.19mm\n",
      "Ep 1480 | R: 1545.4 | Len: 339 | R/s:  4.56 (570.1%) | Gap: 17.26mm (min:15.87) | Best: 13.19mm\n",
      "Ep 1500 | R:  862.8 | Len: 201 | R/s:  4.29 (536.3%) | Gap: 16.17mm (min:14.88) | Best: 13.19mm\n",
      "Ep 1520 | R:  809.8 | Len: 193 | R/s:  4.20 (524.6%) | Gap: 16.03mm (min:14.74) | Best: 13.19mm\n",
      "Ep 1540 | R:  861.1 | Len: 204 | R/s:  4.22 (527.7%) | Gap: 16.25mm (min:14.93) | Best: 13.19mm\n",
      "Ep 1560 | R: 1445.2 | Len: 329 | R/s:  4.40 (549.4%) | Gap: 17.24mm (min:15.19) | Best: 13.19mm\n",
      "Ep 1580 | R: 1993.4 | Len: 486 | R/s:  4.11 (513.2%) | Gap: 18.55mm (min:16.26) | Best: 13.19mm\n",
      "Ep 1600 | R: 1985.4 | Len: 500 | R/s:  3.97 (496.4%) | Gap: 18.75mm (min:18.57) | Best: 13.19mm\n",
      "Ep 1620 | R: 1776.8 | Len: 500 | R/s:  3.55 (444.2%) | Gap: 18.97mm (min:18.91) | Best: 13.19mm\n",
      "Ep 1640 | R: 1755.2 | Len: 500 | R/s:  3.51 (438.8%) | Gap: 18.99mm (min:18.97) | Best: 13.19mm\n",
      "Ep 1660 | R: 1751.1 | Len: 500 | R/s:  3.50 (437.8%) | Gap: 19.00mm (min:19.00) | Best: 13.19mm\n",
      "Ep 1680 | R: 1746.6 | Len: 500 | R/s:  3.49 (436.7%) | Gap: 19.00mm (min:19.00) | Best: 13.19mm\n",
      "Ep 1700 | R: 1746.2 | Len: 500 | R/s:  3.49 (436.5%) | Gap: 19.00mm (min:19.00) | Best: 13.19mm\n",
      "Ep 1720 | R: 1747.8 | Len: 500 | R/s:  3.50 (437.0%) | Gap: 19.00mm (min:19.00) | Best: 13.19mm\n",
      "Ep 1740 | R: 1743.0 | Len: 500 | R/s:  3.49 (435.8%) | Gap: 19.00mm (min:19.00) | Best: 13.19mm\n",
      "Ep 1760 | R: 1743.4 | Len: 500 | R/s:  3.49 (435.8%) | Gap: 19.00mm (min:19.00) | Best: 13.19mm\n",
      "Ep 1780 | R: 1744.3 | Len: 500 | R/s:  3.49 (436.1%) | Gap: 19.00mm (min:19.00) | Best: 13.19mm\n",
      "Ep 1800 | R: 1744.0 | Len: 500 | R/s:  3.49 (436.0%) | Gap: 19.00mm (min:19.00) | Best: 13.19mm\n",
      "Ep 1820 | R: 1739.4 | Len: 500 | R/s:  3.48 (434.8%) | Gap: 19.00mm (min:19.00) | Best: 13.19mm\n",
      "Ep 1840 | R: 1736.2 | Len: 500 | R/s:  3.47 (434.1%) | Gap: 19.00mm (min:19.00) | Best: 13.19mm\n",
      "Ep 1860 | R: 1732.7 | Len: 500 | R/s:  3.47 (433.2%) | Gap: 19.00mm (min:19.00) | Best: 13.19mm\n",
      "Ep 1880 | R: 1732.1 | Len: 500 | R/s:  3.46 (433.0%) | Gap: 19.00mm (min:19.00) | Best: 13.19mm\n",
      "Ep 1900 | R: 1732.2 | Len: 500 | R/s:  3.46 (433.0%) | Gap: 19.00mm (min:19.00) | Best: 13.19mm\n",
      "Ep 1920 | R: 1729.1 | Len: 500 | R/s:  3.46 (432.3%) | Gap: 19.00mm (min:19.00) | Best: 13.19mm\n",
      "Ep 1940 | R: 1728.6 | Len: 500 | R/s:  3.46 (432.1%) | Gap: 19.00mm (min:19.00) | Best: 13.19mm\n",
      "Ep 1960 | R: 1728.0 | Len: 500 | R/s:  3.46 (432.0%) | Gap: 19.00mm (min:19.00) | Best: 13.19mm\n",
      "Ep 1980 | R: 1728.5 | Len: 500 | R/s:  3.46 (432.1%) | Gap: 19.00mm (min:19.00) | Best: 13.19mm\n",
      "Ep 2000 | R: 1726.8 | Len: 500 | R/s:  3.45 (431.7%) | Gap: 19.00mm (min:19.00) | Best: 13.19mm\n"
     ]
    }
   ],
   "source": [
    "# Training Loop with Better Monitoring\n",
    "ep_rewards = []\n",
    "ep_lengths = []\n",
    "ep_gap_errors = []\n",
    "best_gap_error = float('inf')\n",
    "gui_env = None\n",
    "\n",
    "for episode_idx in range(num_episodes):\n",
    "  train_data, ep_reward, gap_error = rollout(model, environ)\n",
    "  \n",
    "  ep_length = len(train_data[0])\n",
    "  ep_rewards.append(ep_reward)\n",
    "  ep_lengths.append(ep_length)\n",
    "  ep_gap_errors.append(gap_error)\n",
    "  \n",
    "  # Track best performance\n",
    "  if gap_error < best_gap_error:\n",
    "    best_gap_error = gap_error\n",
    "\n",
    "  # Data Formatting\n",
    "  permute_idxs = np.random.permutation(len(train_data[0]))\n",
    "  obs = torch.tensor(train_data[0][permute_idxs], dtype=torch.float32, device=device)\n",
    "  acts = torch.tensor(train_data[1][permute_idxs], dtype=torch.float32, device=device)\n",
    "  gaes = torch.tensor(train_data[3][permute_idxs], dtype=torch.float32, device=device)\n",
    "  act_log_probs = torch.tensor(train_data[4][permute_idxs], dtype=torch.float32, device=device)\n",
    "\n",
    "  returns = discount_rewards(train_data[2])[permute_idxs]\n",
    "  returns = torch.tensor(returns, dtype=torch.float32, device=device)\n",
    "\n",
    "  # Normalize GAEs for stable training\n",
    "  gaes = (gaes - gaes.mean()) / (gaes.std() + 1e-8)\n",
    "\n",
    "  ppo.train_policy(obs, acts, act_log_probs, gaes)\n",
    "  ppo.train_value(obs, returns)\n",
    "\n",
    "  if (episode_idx + 1) % print_freq == 0:\n",
    "    avg_reward = np.mean(ep_rewards[-print_freq:])\n",
    "    avg_length = np.mean(ep_lengths[-print_freq:])\n",
    "    avg_gap_error = np.mean(ep_gap_errors[-print_freq:])\n",
    "    min_gap_error = np.min(ep_gap_errors[-print_freq:])\n",
    "    avg_reward_per_step = avg_reward / avg_length if avg_length > 0 else 0\n",
    "    \n",
    "    # Updated for new reward scale (realistic good is ~0.8/step)\n",
    "    realistic_good_per_step = 0.8\n",
    "    percent_of_realistic = (avg_reward_per_step / realistic_good_per_step) * 100\n",
    "    \n",
    "    output_line = (f\"Ep {episode_idx + 1:4d} | R: {avg_reward:6.1f} | Len: {avg_length:3.0f} | \"\n",
    "                   f\"R/s: {avg_reward_per_step:5.2f} ({percent_of_realistic:5.1f}%) | \"\n",
    "                   f\"Gap: {avg_gap_error:5.2f}mm (min:{min_gap_error:5.2f}) | Best: {best_gap_error:5.2f}mm\")\n",
    "    \n",
    "    print(output_line)\n",
    "    log_file.write(output_line + \"\\n\")\n",
    "    log_file.flush()\n",
    "\n",
    "# Close GUI environment if created\n",
    "if gui_env is not None:\n",
    "  gui_env.close()\n",
    "\n",
    "# Close log file\n",
    "log_file.write(\"\\n\" + \"=\"*70 + \"\\n\")\n",
    "log_file.write(f\"Training Completed: {datetime.now().strftime('%Y%m%d_%H%M%S')}\\n\")\n",
    "log_file.write(f\"Best Gap Error Achieved: {best_gap_error:.3f} mm\\n\")\n",
    "log_file.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3678193c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "✓ Training log saved to: RL_Trials/training_log_20251211_191801.txt\n",
      "✓ Gap error plot saved to: RL_Trials/gap_error_plot_20251211_191801.png\n"
     ]
    }
   ],
   "source": [
    "# Create and save gap error plot\n",
    "plt.figure(figsize=(12, 6))\n",
    "plt.plot(ep_gap_errors, alpha=0.3, label='Per Episode')\n",
    "\n",
    "# Calculate moving average (window size = print_freq)\n",
    "window_size = print_freq\n",
    "if len(ep_gap_errors) >= window_size:\n",
    "    moving_avg = np.convolve(ep_gap_errors, np.ones(window_size)/window_size, mode='valid')\n",
    "    plt.plot(range(window_size-1, len(ep_gap_errors)), moving_avg, linewidth=2, label=f'{window_size}-Episode Moving Average')\n",
    "\n",
    "plt.xlabel('Episode', fontsize=12)\n",
    "plt.ylabel('Average Gap Height Error (mm)', fontsize=12)\n",
    "plt.title('Gap Height Error Over Training, n_steps=500', fontsize=14, fontweight='bold')\n",
    "plt.legend(fontsize=11)\n",
    "plt.grid(True, alpha=0.3)\n",
    "plt.tight_layout()\n",
    "plt.savefig(plot_file_path, dpi=150, bbox_inches='tight')\n",
    "plt.show()\n",
    "\n",
    "print(f\"\\n✓ Training log saved to: {log_file_path}\")\n",
    "print(f\"✓ Gap error plot saved to: {plot_file_path}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "7c225451",
   "metadata": {},
   "outputs": [],
   "source": [
    "environ.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "97e51696",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "LevSim",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.19"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}