GitHub - saisriramyerubandi/Reinforcement-Learning: The aim of the project is to perform Q-learning on a historical stock price for Nvidia for the last 5 years dataset which is reinforcement learning. I have trained the agent by using temporal difference and performed Q - Learning . I was able to successfully construct a Q -Table at the end of training . I Used this Q-table to evaluate the algorithm by considering the initial capital 100000 and Total account value at the end. We can see that we ended up in profits and we can say that our algorithm is good

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 3 Commits
NVDA.csv		NVDA.csv
Qlearning.ipynb		Qlearning.ipynb

About

The aim of the project is to perform Q-learning on a historical stock price for Nvidia for the last 5 years dataset which is reinforcement learning. I have trained the agent by using temporal difference and performed Q - Learning . I was able to successfully construct a Q -Table at the end of training . I Used this Q-table to evaluate the algori…

reinforcement-learning qlearning-algorithm reinforcement-learning-agent reinforcement-learning-environments