Open niceban opened 1 year ago
After we update the code from single env to vectorized env, Pull Request: single env to vectorized env, the code adaptation has only been done for the single RL algorithm, and the adaptation for multiple intelligences is not yet complete.
We will continue to update the code of MAEL algorithm after completing the algorithm of Hterm. Thank you for your reminder.
when could your team close those bugs.
AgentMATD3
&AgentMADDPG
cannot be call bytrain_agent
ortrain_agent_multiprocessing
, when I add them to 'demo_DDPG_TD3_SAC.py'Error shows like that
Traceback (most recent call last): File "/Users/c/Downloads/ElegantRL-master/examples/demo_DDPG_TD3_SAC.py", line 238, in
train_ddpg_td3_sac_for_pendulum()
File "/Users/c/Downloads/ElegantRL-master/examples/demo_DDPG_TD3_SAC.py", line 43, in train_ddpg_td3_sac_for_pendulum
train_agent_multiprocessing(args) # train_agent(args)
File "/Users/c/Downloads/ElegantRL-master/elegantrl/train/run.py", line 124, in train_agent_multiprocessing
[process.start() for process in process_list]
File "/Users/c/Downloads/ElegantRL-master/elegantrl/train/run.py", line 124, in
[process.start() for process in process_list]
File "/opt/anaconda3/envs/erl/lib/python3.9/multiprocessing/process.py", line 121, in start
self._popen = self._Popen(self)
File "/opt/anaconda3/envs/erl/lib/python3.9/multiprocessing/context.py", line 224, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "/opt/anaconda3/envs/erl/lib/python3.9/multiprocessing/context.py", line 291, in _Popen
return Popen(process_obj)
File "/opt/anaconda3/envs/erl/lib/python3.9/multiprocessing/popen_forkserver.py", line 35, in init
super().init(process_obj)
File "/opt/anaconda3/envs/erl/lib/python3.9/multiprocessing/popen_fork.py", line 19, in init
self._launch(process_obj)
File "/opt/anaconda3/envs/erl/lib/python3.9/multiprocessing/popen_forkserver.py", line 47, in _launch
reduction.dump(process_obj, buf)
File "/opt/anaconda3/envs/erl/lib/python3.9/multiprocessing/reduction.py", line 60, in dump
ForkingPickler(file, protocol).dump(obj)
TypeError: cannot pickle 'module' object