Open utterances-bot opened 1 year ago
In this post, We will take a hands-on-lab of Simple Deep Q-Network (DQN) on openAI LunarLander-v2 environment. This is the coding exercise from udacity Deep Reinforcement Learning Nanodegree.
https://goodboychan.github.io/python/reinforcement_learning/pytorch/udacity/2021/05/07/DQN-LunarLander.html
Awesome example! But seems there is memory leak in the code. When I change the parameter size to a bigger one, the issue becomes more apparent.
Deep Q-Network (DQN) on LunarLander-v2 | Chan`s Jupyter
In this post, We will take a hands-on-lab of Simple Deep Q-Network (DQN) on openAI LunarLander-v2 environment. This is the coding exercise from udacity Deep Reinforcement Learning Nanodegree.
https://goodboychan.github.io/python/reinforcement_learning/pytorch/udacity/2021/05/07/DQN-LunarLander.html