Pull stock prices from online API and perform predictions using Recurrent Neural Network and Long Short-Term Memory (LSTM) with TensorFlow.js framework. Reinforcement learning algorithm for agents to learn the tic-tac-toe, using the value function. Train the agent to play tic-tac-toe, by having 2 agents play against each other through simulation. You can experiment by adjusting 2 parameters, 1) learning rate and 2) probability of exploration of each agent. After training, try playing against the agent.