Assuming I have a well-trained DQN model and observations. How can I get the Q-value for each potential action by input the current observations.
I am expecting something like the following:
model = DQN.load("dqn_cartpole")
env = gym.make("CartPole-v1")
obs = env.reset()
action = 1
q_values = model.q_values(obs)
q_value = q_values[action]