This repository contains my projects for Reinforcement Learning (CSCI181V).
- Q-Learning: Model-free reinforcement learning algorithm that seeks to find the best action to take given the current state. It does this by learning a Q-value function that estimates the expected utility of taking a given action in a given state.
- Qtable: A table that stores Q-values for each state-action pair.
- Qnetwork: A neural network that approximates the Q-value function.
- QNN with buffer: A Q-network with experience replay buffer to store and reuse past experiences.
- DQN: Deep Q-Network that uses deep neural networks to approximate the Q-value function.