PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).
in main.py
it stops when args.eval_interval is not None:
if (args.eval_interval is not None and len(episode_rewards) > 1 and j % args.eval_interval == 0): ob_rms = utils.get_vec_normalize(envs).ob_rms evaluate(actor_critic, ob_rms, args.env_name, args.seed, args.num_processes, eval_log_dir, device)
in beseline :
it seems to be wrong in "cmd, data = pipe.recv()"
EOFError Process ForkProcess-1: Traceback (most recent call last): File "/home/u/anaconda3/lib/python3.8/multiprocessing/process.py", line 315, in _bootstrap self.run() File "/home/u/anaconda3/lib/python3.8/multiprocessing/process.py", line 108, in run self._target(*self._args, **self._kwargs) File "/home/u/anaconda3/lib/python3.8/site-packages/baselines/common/vec_env/shmem_vec_env.py", line 124, in _subproc_worker cmd, data = pipe.recv() File "/home/u/anaconda3/lib/python3.8/multiprocessing/connection.py", line 250, in recv buf = self._recv_bytes() File "/home/u/anaconda3/lib/python3.8/multiprocessing/connection.py", line 414, in _recv_bytes buf = self._recv(4) File "/home/u/anaconda3/lib/python3.8/multiprocessing/connection.py", line 383, in _recv raise EOFError
in main.py it stops when args.eval_interval is not None:
if (args.eval_interval is not None and len(episode_rewards) > 1 and j % args.eval_interval == 0): ob_rms = utils.get_vec_normalize(envs).ob_rms evaluate(actor_critic, ob_rms, args.env_name, args.seed, args.num_processes, eval_log_dir, device)
in beseline : it seems to be wrong in "cmd, data = pipe.recv()"
The error log is here:
EOFError Process ForkProcess-1: Traceback (most recent call last): File "/home/u/anaconda3/lib/python3.8/multiprocessing/process.py", line 315, in _bootstrap self.run() File "/home/u/anaconda3/lib/python3.8/multiprocessing/process.py", line 108, in run self._target(*self._args, **self._kwargs) File "/home/u/anaconda3/lib/python3.8/site-packages/baselines/common/vec_env/shmem_vec_env.py", line 124, in _subproc_worker cmd, data = pipe.recv() File "/home/u/anaconda3/lib/python3.8/multiprocessing/connection.py", line 250, in recv buf = self._recv_bytes() File "/home/u/anaconda3/lib/python3.8/multiprocessing/connection.py", line 414, in _recv_bytes buf = self._recv(4) File "/home/u/anaconda3/lib/python3.8/multiprocessing/connection.py", line 383, in _recv raise EOFError