dobro12 / cpo Goto Github PK

import torch
import argparse
from env import Env
from agent import Agent

def inference(saved_model_path, num_episodes):
    device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

    seed = 10
    max_ep_len = 1000
    max_steps = 4000
    
    # Load the trained agent and its checkpoint
    loaded_checkpoint = torch.load(saved_model_path, map_location=device)
    
    env_name = "Safexp-PointGoal1-v0"
    env = Env(env_name, seed, max_ep_len)

    args = {
        'agent_name':'CPO',
        'save_name':'',
        'discount_factor':0.99,
        'hidden1':512,
        'hidden2':512,
        'v_lr':2e-4,
        'cost_v_lr':2e-4,
        'value_epochs':200,
        'batch_size':10000,
        'num_conjugate':10,
        'max_decay_num':10,
        'line_decay':0.8,
        'max_kl':0.001,
        'damping_coeff':0.01,
        'gae_coeff':0.97,
        'cost_d':25.0/1000.0,
    }
    
    # Initialize the agent with the necessary arguments
    agent = Agent(env, device, args)
    
    agent.policy.load_state_dict(loaded_checkpoint['policy'])
    agent.value.load_state_dict(loaded_checkpoint['value'])
    agent.cost_value.load_state_dict(loaded_checkpoint['cost_value'])
    
    for _ in range(num_episodes):
        state = env.reset()
        total_reward = 0
        
        for step in range(max_steps):
            state_tensor = torch.tensor(state, device=device, dtype=torch.float)
            action_tensor, _ = agent.getAction(state_tensor, is_train=False)
            action = action_tensor.detach().cpu().numpy()
            
            next_state, reward, done, _ = env.step(action)
            total_reward += reward
            
            state = next_state
            
            if done:
                print(f"Episode reward: {total_reward}")
                break

if __name__ == "__main__":
    parser = argparse.ArgumentParser(description='Inference using a saved model')
    parser.add_argument('saved_model_path', type=str, help='Path to the saved model checkpoint')
    parser.add_argument('--num_episodes', type=int, default=10, help='Number of episodes for inference')
    args = parser.parse_args()
    
    inference(args.saved_model_path, args.num_episodes)

Traceback (most recent call last):
  File "inference.py", line 69, in <module>
    inference(args.saved_model_path, args.num_episodes)
  File "inference.py", line 39, in inference
    agent = Agent(env, device, args)
  File ".../CPO/torch/agent.py", line 84, in __init__
    self.load()
  File ".../CPO/torch/agent.py", line 367, in load
    os.makedirs(self.checkpoint_dir)
  File ".../anaconda3/envs/cpo-only-env/lib/python3.6/os.py", line 220, in makedirs
    mkdir(name, mode)
PermissionError: [Errno 13] Permission denied: '/checkpoint'