test_grid2op.py

"""Test script for debugging the Grid2Op environment."""
from envs.grid2op_env import Grid2opEnvWrapper


def test_grid2op_env():
    """Test basic Grid2Op environment functionality."""
    
    # Configuration for the Grid2Op environment
    env_config = {
        "env_name": "l2rpn_case14_sandbox",
        "env_is_test": True,
        "act_type": "discrete",
        "obs_attr_to_keep": ["rho", "p_or"],
        "act_attr_to_keep": ["set_line_status_simple"]
    }
    
    print("Creating Grid2Op environment...")
    env = Grid2opEnvWrapper(
        horizon=100,
        gamma=0.99,
        render=False,
        clip=True,
        env_config=env_config
    )
    
    print(f"Observation space: {env.observation_space}")
    print(f"Action space: {env.action_space}")
    print(f"State dim: {env.state_dim}")
    print(f"Action dim: {env.action_dim}")
    
    # Reset the environment
    print("\nResetting environment...")
    obs, info = env.reset()
    print(f"Initial observation shape: {obs.shape}")
    print(f"Initial observation: {obs[:10]}...")  # Print first 10 values
    
    # Run a few steps with random actions
    print("\nRunning 10 random steps...")
    total_reward = 0
    for step in range(10):
        # Sample a random action
        action = env.action_space.sample()
        
        # Take a step
        obs, reward, done, info = env.step(action)
        total_reward += reward
        
        print(f"Step {step + 1}: action={action}, reward={reward:.4f}, "
              f"done={done}")
        
        if done:
            print("Episode ended early!")
            obs, info = env.reset()
    
    print(f"\nTotal reward over 10 steps: {total_reward:.4f}")
    print("\nGrid2Op environment test completed successfully!")


if __name__ == "__main__":
    test_grid2op_env()