Spaces:
Sleeping
Sleeping
File size: 1,603 Bytes
a448db8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 | import pandas as pd
import matplotlib.pyplot as plt
import os
def main():
os.makedirs('results', exist_ok=True)
if not os.path.exists('rewards_log.csv'):
print("No rewards_log.csv found. Run inference first.")
return
try:
df = pd.read_csv('rewards_log.csv')
except Exception as e:
print(f"Error reading CSV: {e}")
return
if df.empty:
print("rewards_log.csv is empty.")
return
# Plot 1: Reward Curve over Training Steps (using index as training step)
plt.figure(figsize=(10, 6))
plt.plot(df.index, df['reward'], alpha=0.3, label='Episode Reward')
# 10-step rolling average
rolling_avg = df['reward'].rolling(window=10, min_periods=1).mean()
plt.plot(df.index, rolling_avg, color='red', linewidth=2, label='10-step Rolling Average')
plt.xlabel('Training Step')
plt.ylabel('Episode Reward (0-1)')
plt.title('Reward Curve')
plt.legend()
plt.grid(True, alpha=0.3)
plt.savefig('results/reward_curve.png')
plt.close()
# Plot 2: Average Reward per Task ID
plt.figure(figsize=(10, 6))
avg_per_task = df.groupby('task_id')['reward'].mean().sort_values()
avg_per_task.plot(kind='barh', color='skyblue')
plt.xlabel('Average Episode Reward (0-1)')
plt.ylabel('Task ID')
plt.title('Average Reward by Task ID')
plt.grid(axis='x', alpha=0.3)
plt.tight_layout()
plt.savefig('results/reward_by_task.png')
plt.close()
print("Plots saved to results/ directory.")
if __name__ == "__main__":
main()
|