Multiple hypothesis testing in Python

Implementation of the Double Deep Q-Learning algorithm with a prioritized experience replay memory to train an agent to play the minichess variante Gardner Chess

Implementation of the MDP algorithm for optimal decision-making, focusing on value iteration and policy determination.

Q-learning and Q-value iteration algorithms for the Block-World environment.

Build an RL (Reinforcement Learning) agent that learns to play Numerical Tic-Tac-Toe. The agent learns the game by Q-Learning.

🐍 The Project is based on Reinforcement Learning which trains the snake to eat the food present in the environment.

Estimate (Local) False Discovery Rates with Weights, adapted from fdrtool

Q-Value (Reinforcement Learning) on Grid World