meet problems when training

[rainbow979]

I run the train_food_epc.sh and meet the error:

Traceback (most recent call last): File "/home/chuangg/miniconda3/envs/sy/lib/python3.7/multiprocessing/process.py", line 297, in _bootstrap self.run() File "/home/chuangg/epciclr2020/maddpg_o/experiments/train_helper/proxy_train.py", line 13, in run self.conn.send(train(**self.kwargs)) File "/home/chuangg/epciclr2020/maddpg_o/experiments/train_helper/train_helpers.py", line 1141, in train update_time += time.time() - t_update File "/home/chuangg/miniconda3/envs/sy/lib/python3.7/tempfile.py", line 807, in __exit__ self.cleanup() File "/home/chuangg/miniconda3/envs/sy/lib/python3.7/tempfile.py", line 811, in cleanup _shutil.rmtree(self.name) File "/home/chuangg/miniconda3/envs/sy/lib/python3.7/shutil.py", line 494, in rmtree _rmtree_safe_fd(fd, path, onerror) File "/home/chuangg/miniconda3/envs/sy/lib/python3.7/shutil.py", line 413, in _rmtree_safe_fd onerror(os.scandir, path, sys.exc_info()) File "/home/chuangg/miniconda3/envs/sy/lib/python3.7/shutil.py", line 409, in _rmtree_safe_fd with os.scandir(topfd) as scandir_it: OSError: [Errno 24] Too many open files: '/tmp/tmpxrsu4eub'