zyh1999 / CADP

Is Centralized Training with Decentralized Execution Framework Centralized Enough for MARL?
Apache License 2.0
19 stars 4 forks source link

KeyError: 'unit_dim' #1

Closed Isaac009 closed 6 months ago

Isaac009 commented 7 months ago

Hello author,

I got this error when I ran the code to replicate the results: marl_env/lib/python3.8/site-packages/gym/logger.py:30: UserWarning: WARN: Could not seed environment warnings.warn(colorize('%s: %s'%('WARN', msg % args), 'yellow')) [DEBUG 12:57:47] pymarl Stopping Heartbeat [ERROR 12:57:47] pymarl Failed after 0:00:01! Traceback (most recent call last): File "marl_env/lib/python3.8/site-packages/sacred/experiment.py", line 312, in run_commandline return self.run( File "marl_env/lib/python3.8/site-packages/sacred/experiment.py", line 276, in run run() File "marl_env/lib/python3.8/site-packages/sacred/run.py", line 238, in call self.result = self.main_function(args) File "marl_env/lib/python3.8/site-packages/sacred/config/captured_function.py", line 42, in captured_function result = wrapped(args, **kwargs) File "CADP/CADP-VD/src/main.py", line 35, in my_main run(_run, config, _log) File "MARL/CADP/CADP-VD/src/run.py", line 48, in run run_sequential(args=args, logger=logger) File "/home/jupyter-isack/Documents/PBCS/MASER/CADP/CADP-VD/src/run.py", line 86, in run_sequential args.unit_dim = env_info["unit_dim"] KeyError: 'unit_dim'

The command I ran: python3 CADP-VD/src/main.py --config=QMIX_CADP --env-config=gfootball with env_args.map_name=academy_3_vs_1_with_keeper optimizer='rmsprop'

zyh1999 commented 6 months ago

Thank you for your feedback. I indeed overlooked this issue. Please disregard the mentioned sentence “File "/home/jupyter-isack/Documents/PBCS/MASER/CADP/CADP-VD/src/run.py", line 86, in run_sequential args.unit_dim = env_info["unit_dim"]” as it has been deleted. I have already updated the version, rectifying this bug.