The Repository contains multiple Project on Reinforcement Learning.

Unsupervised Learning on OpenAI Gym to understand the properties of such algorithms, using Value Iteration and Q-Learning algorithmn. Developed with my coding friend @jibrilsharafi.

Experience the fusion of finance and artificial intelligence with this cutting-edge project that implements a deep reinforcement learning agent for automated stock trading. Leveraging advanced neural network architectures and a meticulously crafted reward function, the agent learns to make profitable trading decisions in a simulated environment

Development of ns-3 simulation scenery using on openAiGym, Lorawan and NR-5G modules.

this repo keeps track of RL course