Closed bscoventry closed 3 years ago
Hi,
When trying out different algorithms, I run into an import error for A2C. Code is from Advantage actor critic sample in the wiki:
import gym from genrl import A2C from genrl.deep.common import OnPolicyTrainer from genrl.environments import VectorEnv env = VectorEnv("CartPole-v0") agent = A2C('mlp', env) trainer = OnPolicyTrainer(agent, env, log_mode=['stdout']) trainer.train()
and fails with ImportError: cannot import name 'A2C'
Setup is Python 3.6.8, Cuda 10.1
Could you try from genrl.agents import A2C instead? That might fix it for now.
from genrl.agents import A2C
Hi,
When trying out different algorithms, I run into an import error for A2C. Code is from Advantage actor critic sample in the wiki:
and fails with ImportError: cannot import name 'A2C'
Setup is Python 3.6.8, Cuda 10.1