gsurma/cartpole

OpenAI's cartpole env solver.

Hi there 👋

Blog
Portfolio

cartpole's Issues

It is NOT a DQN, but good job

You had a good idea to test LightGBM on Q-Learning, but the class name is wrong :(

Definition of DQN: DQN (Deep-Q-Network)

How's your code is different from https://github.com/keon/deep-q-learning?

List index out of range error

If I run cartpole.py I am getting list index out of range error

reward is strange

This line
q_update = (reward + GAMMA * np.amax(self.model.predict(state_next)[0]))

you are taking a prediction upon your next state, and then updating your current predictions with a reward over that (next) state.

q_values = self.model.predict(state)
q_values[0][action] = q_update

So you are essentially rewarding your model for the next action it takes. The reason this works is that rewards in future states are dependent upon current actions. So your model trains, but it's doing so in a strange way.