keras-rl / keras-rl

Deep Reinforcement Learning for Keras.

Home Page:http://keras-rl.readthedocs.io/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

raise ValueError 'Critic "{}" does not have enough inputs when run ddpg_pendulum.py

HankerSia opened this issue · comments

Traceback (most recent call last):
File "examples/ddpg_pendulum.py", line 57, in
random_process=random_process, gamma=.99, target_model_update=1e-3)
File "/home/kai/keras-rl/rl/agents/ddpg.py", line 36, in init
raise ValueError('Critic "{}" does not have enough inputs. The critic must have at exactly two inputs, one for the action and one for the observation.'.format(critic))
ValueError: Critic "<keras.engine.training.Model object at 0x7fae6e05d690>" does not have enough inputs. The critic must have at exactly two inputs, one for the action and one for the observation.

it showed errors when i try to run command python examples/ddpg_pendulum.py

btw, python examples/dqn_cartpole.py can be executed successfully.

commented

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.