This repository provides an introductory series to reinforcement learning (RL) with step-by-step tutorials for coding various RL techniques. It targets students and practitioners looking to understand and implement fundamental RL algorithms, offering practical examples and code walkthroughs.

How It Works

The project walks through implementing core RL algorithms like Q-learning, SARSA, Deep Q-learning (DQN), and Deep Deterministic Policy Gradients (DDPG). It leverages OpenAI Gym for environment interaction and demonstrates applications in simulated environments like ROS/Gazebo and potentially DOOM, offering a practical, code-centric approach to learning.

Quick Start & Requirements

• Install via pip.
• Requires Python and OpenAI Gym. Specific versions are not detailed.
• Links to OpenAI Gym docs: https://gym.openai.com/docs

Highlighted Details

• Covers a range of RL algorithms from basic Q-learning to deep methods like DQN and DDPG.
• Includes tutorials for integrating RL with ROS and Gazebo.
• Benchmarking of RL techniques is planned.
• References include seminal works and curated RL resources.

Maintenance & Community

• Maintained by vmayoral.
• No explicit community links (Discord, Slack) or roadmap are provided in the README.

Licensing & Compatibility

• License type is not specified in the README.
• Compatibility for commercial use or closed-source linking is undetermined.

Limitations & Caveats

Several tutorials (8, 10, 13, 15) are marked as unfinished, WIP, or failed, indicating potential incompleteness or instability in certain areas. The lack of specified licensing also poses a potential adoption blocker.