Open Somjit77 opened 2 years ago
In simple_dqn.py, the epsilon schedule is chosen by actor_state.count however, that keeps getting reinitialized after every episode in experiment.py. So the epsilon schedule does not work.
In simple_dqn.py, the epsilon schedule is chosen by actor_state.count however, that keeps getting reinitialized after every episode in experiment.py. So the epsilon schedule does not work.