search

openai / maddpg

Code for the MADDPG algorithm from the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"
https://arxiv.org/pdf/1706.02275.pdf
MIT License
1.59k stars 484 forks source link

Using any scenario rather than the "simple" one gives error during loading the model after training #58

Closed dr-smgad closed 3 years ago

dr-smgad commented 3 years ago

I am running the experiment on Windows 10 OS.

Train command example: python experiments\train.py --scenario simple_push --num-episodes 2000 --exp-name demo1

Load command used: python experiments\train.py --scenario simple_push --num-episodes 1000 --exp-name demo1

Error: Loading previous state... Traceback (most recent call last): File "C:\Users\smmohame\anaconda3\envs\marl_env\lib\site-packages\tensorflow\python\client\session.py", line 1322, in _do_call return fn(*args) File "C:\Users\smmohame\anaconda3\envs\marl_env\lib\site-packages\tensorflow\python\client\session.py", line 1307, in _run_fn options, feed_dict, fetch_list, target_list, run_metadata) File "C:\Users\smmohame\anaconda3\envs\marl_env\lib\site-packages\tensorflow\python\client\session.py", line 1409, in _call_tf_sessionrun run_metadata) tensorflow.python.framework.errors_impl.InvalidArgumentError: Assign requires shapes of both tensors to match. lhs shape= [4,64] rhs shape= [8,64] [[Node: save/Assign_39 = Assign[T=DT_FLOAT, _class=["loc:@agent_0/target_p_func/fully_connected/weights"], use_locking=true, validate_shape=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](agent_0/target_p_func/fully_connected/weights, save/RestoreV2:39)]]