farismismar / q-learning-power-control Goto Github PK

from environment import radio_environment
#from DQNLearningAgent import DQNLearningAgent as QLearner # Deep with GPU and CPU fallback
from QLearningAgent import QLearningAgent as QLearner

#    run_agent_fpa(env)
    run_agent_tabular(env)
#    run_agent_deep(env)

> Ep. | TS | Recv. SINR (srv) | Recv. SINR (int) | Serv. Tx Pwr | Int. Tx Pwr | Reward 
> ------------------------------------------------------------------------------------------------------------
> [-311.94796062  325.77365607  617.88366191 -146.98785931  2.94720088  13.78845061]    
> Traceback (most recent call last):
>   File "main_modify.py", line 592, in <module>
>     run_agent_tabular(env)
>   File "main_modify.py", line 56, in run_agent_tabular
>     action = agent.begin_episode(observation)
>   File "/home/nemo/workspace/Q-Learning-Power-Control/voice/QLearningAgent.py", line 52, in begin_episode
>     self.state = observation + np.zeros(self.state_size, dtype=int)
> ValueError: operands could not be broadcast together with shapes (6,) (3,)