I tried running same code on my machine but after many epochs it just learn to always go right resulting in an score of 8-15. in every random state. https://send.firefox.com/download/675760e4f24d290e/#75lHESF6DgrDhBWPn06GGA
please help
Model Not giving desired Output
Hey @codingblocksml5, reinforcement learning is not an easy task, we need to tune hyperparameters as well, i would recommend try running code in this repo, https://github.com/coding-blocks-archives/machine-learning-online-2018/tree/master/Reinforcement%20Learning
And if it runs fine that match code line by line from your code.
Hope this resolved your doubt.
Plz mark the doubt as resolved in my doubts section.