This repository contains my solutions to exercises and projects of Udacity's Deep Reinforcement Learning Nanodegree program. The original repository can be found here.
The exercises lead us through implementing various algorithms in reinforcement learning.
- Monte Carlo: Implement Monte Carlo methods for prediction and control.
- Temporal-Difference: Implement Temporal-Difference methods such as Sarsa, Q-Learning, and Expected Sarsa.
- The Taxi Problem: In this lab, we train a taxi to pick up and drop off passengers.
- Discretization: Learn how to discretize continuous state spaces, and solve the Mountain Car environment.
- Tile Coding: Implement a method for discretizing continuous state spaces that enables better generalization.
- Deep Q-Network: Explore how to use a Deep Q-Network (DQN) to navigate a space vehicle without crashing.
- Hill Climbing: Use hill climbing with adaptive noise scaling to balance a pole on a moving cart.
- Cross-Entropy Method: Use the cross-entropy method to train a car to navigate a steep hill.
- REINFORCE: Learn how to use Monte Carlo Policy Gradients to solve a classic control task.
- Proximal Policy Optimization: Use PPO to train an agent to play Pong Game.
- AlphaZero: Case study of AlphaZero in the TicTacToe Game.
- Multi-Agent Deep Deterministic Policy Gradient: Learn MADDPG to train several agents to solve the Physical Deception problem.
The projects can be found below. All of the projects use rich simulation environments from Unity ML-Agents.
- Navigation: In the first project, we train an agent to collect yellow bananas while avoiding blue bananas.
- Continuous Control: In the second project, we train a robotic arm to reach target locations.
- Collaboration and Competition: In the third project, we train a pair of agents to play tennis.