pong-ram
It is an attempt to solve Pong-ramNoFrameskip-v4 using SARSA implementation. I'm not optimizing for code legibility or maintainability here.
##Disclaimer This repo uses code from the following places:
- https://gist.github.com/karpathy/a4166c7fe253700972fcbc77e4ea32c5
- https://spinningup.openai.com/en/latest/spinningup/rl_intro3.html
- https://github.com/pytorch/examples/blob/master/reinforcement_learning/reinforce.py
- https://github.com/PacktPublishing/Reinforcement-Learning-Algorithms-with-Python/blob/master/Chapter04/SARSA%20Q_learning%20Taxi-v2.py
- https://www.scirp.org/pdf/jdaip_2016101714072270.pdf
- https://github.com/rogerxcn/lunar_lander_project/blob/master/sarsa_agent.py
- https://arxiv.org/abs/2011.11850
And other resources I could no longer find on my machine