fix(ppo): 修正日志概率维度与状态张量格式

修复 replay buffer 中 log_probs 的维度错误，从 (buffer_size, action_dim) 改为 buffer_size
修正训练时状态张量格式，从 (N, H, W, C) 转换为 (N, C, H, W)
更新 collect_rollout 返回观测值并修正 log_prob 计算
添加项目配置文件和训练曲线生成脚本

强化学习个人项目报告/generate_plots.py

@@ -0,0 +1,107 @@
+"""Generate training plots from TensorBoard logs."""
+import os
+import numpy as np
+from tensorboard.backend.event_processing import event_accumulator
+import matplotlib.pyplot as plt
+
+def extract_metrics(log_dir):
+    """Extract metrics from TensorBoard log directory."""
+    ea = event_accumulator.EventAccumulator(log_dir)
+    ea.Reload()
+
+    metrics = {}
+    for tag in ea.Tags()['scalars']:
+        events = ea.Scalars(tag)
+        steps = [e.step for e in events]
+        values = [e.value for e in events]
+        metrics[tag] = {'steps': steps, 'values': values}
+
+    return metrics
+
+def smooth(data, weight=0.6):
+    """Exponential moving average for smoothing."""
+    smoothed = []
+    last = data[0]
+    for point in data:
+        smoothed_val = last * weight + (1 - weight) * point
+        smoothed.append(smoothed_val)
+        last = smoothed_val
+    return smoothed
+
+def plot_training_curves(metrics, save_path):
+    """Plot training curves."""
+    fig, axes = plt.subplots(2, 2, figsize=(14, 10))
+
+    episodes = metrics.get('Reward/Episode', {}).get('steps', [])
+    ep_rewards = metrics.get('Reward/Episode', {}).get('values', [])
+    avg_rewards = metrics.get('Reward/AvgLast10', {}).get('values', [])
+
+    if episodes and ep_rewards:
+        axes[0, 0].plot(episodes, ep_rewards, alpha=0.3, label='Episode Reward')
+        if avg_rewards:
+            axes[0, 0].plot(episodes, smooth(avg_rewards), 'r-', linewidth=2, label='Smoothed (EMA)')
+        axes[0, 0].set_xlabel('Training Steps')
+        axes[0, 0].set_ylabel('Episode Reward')
+        axes[0, 0].set_title('Training Episode Reward')
+        axes[0, 0].legend()
+        axes[0, 0].grid(True, alpha=0.3)
+
+    eval_steps = metrics.get('Eval/MeanReturn', {}).get('steps', [])
+    eval_returns = metrics.get('Eval/MeanReturn', {}).get('values', [])
+
+    if eval_steps and eval_returns:
+        axes[0, 1].plot(eval_steps, eval_returns, 'g-', linewidth=2, marker='o', markersize=4)
+        axes[0, 1].set_xlabel('Episode')
+        axes[0, 1].set_ylabel('Mean Evaluation Return')
+        axes[0, 1].set_title('Evaluation Performance')
+        axes[0, 1].grid(True, alpha=0.3)
+
+    actor_loss_steps = metrics.get('Loss/Actor', {}).get('steps', [])
+    actor_losses = metrics.get('Loss/Actor', {}).get('values', [])
+
+    if actor_loss_steps and actor_losses:
+        axes[1, 0].plot(actor_loss_steps, smooth(actor_losses), 'b-', linewidth=1.5)
+        axes[1, 0].set_xlabel('Training Steps')
+        axes[1, 0].set_ylabel('Actor Loss')
+        axes[1, 0].set_title('Actor Loss Over Training')
+        axes[1, 0].grid(True, alpha=0.3)
+
+    critic_loss_steps = metrics.get('Loss/Critic', {}).get('steps', [])
+    critic_losses = metrics.get('Loss/Critic', {}).get('values', [])
+
+    if critic_loss_steps and critic_losses:
+        axes[1, 1].plot(critic_loss_steps, smooth(critic_losses), 'purple', linewidth=1.5)
+        axes[1, 1].set_xlabel('Training Steps')
+        axes[1, 1].set_ylabel('Critic Loss')
+        axes[1, 1].set_title('Critic Loss Over Training')
+        axes[1, 1].grid(True, alpha=0.3)
+
+    plt.tight_layout()
+    plt.savefig(save_path, dpi=150, bbox_inches='tight')
+    plt.close()
+    print(f"Plots saved to {save_path}")
+
+def main():
+    log_base = 'logs/tensorboard'
+
+    runs = sorted([d for d in os.listdir(log_base) if os.path.isdir(os.path.join(log_base, d))])
+
+    if not runs:
+        print("No runs found!")
+        return
+
+    latest_run = os.path.join(log_base, runs[-1])
+    print(f"Analyzing run: {runs[-1]}")
+
+    metrics = extract_metrics(latest_run)
+
+    plot_training_curves(metrics, 'training_curves.png')
+
+    print("\nExtracted metrics:")
+    for tag, data in metrics.items():
+        if data['values']:
+            values = np.array(data['values'])
+            print(f"  {tag}: min={values.min():.2f}, max={values.max():.2f}, final={values[-1]:.2f}")
+
+if __name__ == '__main__':
+    main()

强化学习个人项目报告/pyproject.toml

@@ -0,0 +1,39 @@
+[project]
+name = "ppo-carracing"
+version = "0.1.0"
+description = "PPO (Proximal Policy Optimization) for CarRacing-v3 environment"
+requires-python = ">=3.10"
+dependencies = [
+    "torch>=2.0.0",
+    "gymnasium[box2d]>=0.29.0",
+    "numpy>=1.24.0",
+    "matplotlib>=3.7.0",
+    "tensorboard>=2.14.0",
+    "opencv-python>=4.8.0",
+]
+
+[project.optional-dependencies]
+dev = ["pytest>=7.4.0", "black>=23.0.0", "ruff>=0.1.0"]
+
+[project.scripts]
+ppo-train = "train:main"
+ppo-evaluate = "src.evaluate:main"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.ruff]
+line-length = 100
+target-version = "py310"
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "N", "W"]
+ignore = ["E501"]
+
+[tool.black]
+line-length = 100
+target-version = ["py310"]
+
+[tool.hatch.build.targets.wheel]
+packages = ["src"]

强化学习个人项目报告/src/evaluate.py

@@ -1,4 +1,8 @@
 """Evaluation script for trained PPO agent."""
+import sys
+import os
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
 import torch
 import numpy as np
 import gymnasium as gym

强化学习个人项目报告/src/network.py

@@ -1,4 +1,5 @@
 """Neural network architectures for Actor and Critic."""
+
 import torch
 import torch.nn as nn
 import torch.nn.functional as F
@@ -9,7 +10,11 @@ class Actor(nn.Module):
 
     def __init__(self, state_shape=(84, 84, 4), action_dim=3):
         super().__init__()
-        c, h, w = state_shape[2], state_shape[0], state_shape[1]  # channels, height, width
+        c, h, w = (
+            state_shape[2],
+            state_shape[0],
+            state_shape[1],
+        )  # channels, height, width
 
         self.conv = nn.Sequential(
             nn.Conv2d(c, 32, kernel_size=8, stride=4),
@@ -20,8 +25,10 @@ class Actor(nn.Module):
             nn.ReLU(),
         )
 
-        # Calculate feature map size: 84x84 -> 20x20 after conv layers
-        feat_size = 64 * 20 * 20
+        out_h = (h - 8) // 4 + 1
+        out_h = (out_h - 4) // 2 + 1
+        out_h = (out_h - 3) // 1 + 1
+        feat_size = 64 * out_h * out_h
 
         self.fc = nn.Sequential(
             nn.Linear(feat_size, 512),
@@ -62,13 +69,12 @@ class Critic(nn.Module):
             nn.ReLU(),
         )
 
-        feat_size = 64 * 20 * 20
+        out_h = (h - 8) // 4 + 1
+        out_h = (out_h - 4) // 2 + 1
+        out_h = (out_h - 3) // 1 + 1
+        feat_size = 64 * out_h * out_h
 
-        self.fc = nn.Sequential(
-            nn.Linear(feat_size, 512),
-            nn.ReLU(),
-            nn.Linear(512, 1)
-        )
+        self.fc = nn.Sequential(nn.Linear(feat_size, 512), nn.ReLU(), nn.Linear(512, 1))
 
     def forward(self, x):
         """Forward pass returning V(s)."""

强化学习个人项目报告/src/replay_buffer.py

@@ -15,7 +15,7 @@ class RolloutBuffer:
         self.rewards = np.zeros(buffer_size, dtype=np.float32)
         self.dones = np.zeros(buffer_size, dtype=np.bool_)
         self.values = np.zeros(buffer_size, dtype=np.float32)
-        self.log_probs = np.zeros((buffer_size, action_dim), dtype=np.float32)
+        self.log_probs = np.zeros(buffer_size, dtype=np.float32)
 
     def add(self, state, action, reward, done, value, log_prob):
         """Add a transition to the buffer."""

强化学习个人项目报告/src/trainer.py

@@ -56,8 +56,8 @@ class PPOTrainer:
         # Normalize advantages
         advantages = (advantages - advantages.mean()) / (advantages.std() + 1e-8)
 
-        # Convert to tensors
-        states_t = torch.from_numpy(states).float().to(self.device)
+        # Convert to tensors (states: N, H, W, C -> N, C, H, W)
+        states_t = torch.from_numpy(states).float().permute(0, 3, 1, 2).to(self.device)
         actions_t = torch.from_numpy(actions).float().to(self.device)
         log_probs_old_t = torch.from_numpy(log_probs_old).float().to(self.device)
         returns_t = torch.from_numpy(returns).float().to(self.device)
@@ -75,16 +75,13 @@ class PPOTrainer:
             for batch in loader:
                 s, a, log_pi_old, ret, adv = batch
 
-                # Get current policy distribution
                 mu, std = self.actor(s)
                 dist = torch.distributions.Normal(mu, std)
-                log_pi = dist.log_prob(a).sum(dim=-1, keepdim=True)
-                entropy = dist.entropy().sum(dim=-1, keepdim=True)
+                log_pi = dist.log_prob(a).sum(dim=-1)
+                entropy = dist.entropy().sum(dim=-1)
 
-                # Probability ratio
                 ratio = torch.exp(log_pi - log_pi_old)
 
-                # Clipped surrogate objective
                 surr1 = ratio * adv
                 surr2 = torch.clamp(ratio, 1 - self.clip_eps, 1 + self.clip_eps) * adv
                 actor_loss = -torch.min(surr1, surr2).mean()

强化学习个人项目报告/train.py

@@ -30,7 +30,7 @@ def collect_rollout(actor, critic, env, buffer, device, rollout_steps):
             value = critic(obs_t).squeeze(0).item()
 
             action_np = action.squeeze(0).cpu().numpy()
-            log_prob_np = log_prob.squeeze(0).cpu().numpy()
+            log_prob_np = log_prob.squeeze(0).cpu().numpy().sum()
 
         next_obs, reward, terminated, truncated, _ = env.step(action_np)
         done = terminated or truncated
@@ -46,6 +46,8 @@ def collect_rollout(actor, critic, env, buffer, device, rollout_steps):
             obs, _ = env.reset()
             obs = np.transpose(obs, (1, 2, 0))
 
+    return obs
+
 
 def train(
     total_steps=500000,
@@ -102,10 +104,8 @@ def train(
     recent_rewards = []
 
     while total_timesteps < total_steps:
-        # Collect rollout
-        collect_rollout(actor, critic, env, buffer, device, rollout_steps)
+        obs = collect_rollout(actor, critic, env, buffer, device, rollout_steps)
 
-        # Get last value for GAE
         with torch.no_grad():
             obs_t = torch.from_numpy(obs).float().unsqueeze(0).permute(0, 3, 1, 2).to(device)
             last_value = critic(obs_t).squeeze(0).item()
@@ -190,3 +190,13 @@ if __name__ == "__main__":
 
     device = get_device()
     train(total_steps=args.steps, rollout_steps=args.rollout, device=device)
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--steps", type=int, default=500000, help="Total training steps")
+    parser.add_argument("--rollout", type=int, default=2048, help="Rollout buffer size")
+    args = parser.parse_args()
+
+    device = get_device()
+    train(total_steps=args.steps, rollout_steps=args.rollout, device=device)