Test DQN Algorithm on CartPole-v1 | DQN PyTorch Beginners Tutorial #8
Ғылым және технология
In this Deep Q-Learning, aka Deep Q-Network (DQN), tutorial series, we'll code up the algorithm with PyTorch and train FlappyBird. In this video, we finally finish the code for the DQN algorithm and we can test the code against Cart Pole. Cart Pole is a simple environment and it can give me feedback within a few minutes.
Github code: github.com/johnnycode8/dqn_py...
Support me here: www.buymeacoffee.com/johnnycode
Пікірлер: 2
Do you have a discord or something where we can ask questions? I am getting some very strange outputs for my average reward graph. Additionally, my new best reward is struggling to pass 200. Also would you be able to post your source code somewhere so we can compare? I just want to see where our code deviates (if at all). Thanks! Great series so far :D Edit: I tweaked my hyperparameters and now I am getting a much better result! I am new to machine learning so I am getting used to having to play with things like hyperparameters in order to get better results.
@johnnycode
16 күн бұрын
I don't have a discord. You are welcome to drop your questions here. Glad you are able to make some progress. There are a lot of randomness involved in Reinforcement Learning which makes it extra difficult. Here is the final code: github.com/johnnycode8/dqn_pytorch