Running train.py doesn't seem to work
suryabhupa opened this issue · comments
After setting up the multiagent-particle-envs and adding the path to the PYTHONPATH, and after all the pip installs, running the
python train.py --scenario simple
results in:
/home/.local/lib/python3.6/site-packages/tensorflow/python/util/tf_inspect.py:45: DeprecationWarning: inspect.getargspec() is deprecated, use inspect.signature() or inspect.getfullargspec()
if d.decorator_argspec is not None), _inspect.getargspec(target))
Using good policy maddpg and adv policy maddpg
Traceback (most recent call last):
File "train.py", line 195, in
train(arglist)
File "train.py", line 106, in train
obs_n = env.reset()
File "~/gym/gym/core.py", line 71, in reset
raise NotImplementedError
NotImplementedError
Any fixes?
Hi, this is related to the newest version of OpenAI gym (>=0.10), which has made some breaking changes to other code. If you downgrade your version of gym, it should work. We're looking into fixing this.
Should be fixed now!
I downgrade my version of gym to 0.10.0,but it still dose not work.
Hi xiaoy,
The old version of the multiagent-particle-envs code works with gym 0.9.x and lower.
The new version works with gym 0.10.x and higher. So with the new version of both gym and multiagent-particle-envs everything should work. If it doesn't, please raise another issue! :)
why can't I install the old version of gym?
(base) E:\DPL\MA\maddpg-master\maddpg-master\experiments>pip install gym-0.9.2
ERROR: Could not find a version that satisfies the requirement gym-0.9.2 (from v
ersions: none)
ERROR: No matching distribution found for gym-0.9.2