deep-rl-class/units/en/_toctree.yml

- title: Unit 0. Welcome to the course
  sections:
  - local: unit0/introduction
    title: Welcome to the course 🤗
  - local: unit0/setup
    title: Setup
  - local: unit0/discord101
    title: Discord 101
- title: Unit 1. Introduction to Deep Reinforcement Learning
  sections:
  - local: unit1/introduction
    title: Introduction
  - local: unit1/what-is-rl
    title: What is Reinforcement Learning?
  - local: unit1/rl-framework
    title: The Reinforcement Learning Framework
  - local: unit1/tasks
    title: The type of tasks
  - local: unit1/exp-exp-tradeoff
    title: The Exploration/ Exploitation tradeoff
  - local: unit1/two-methods
    title: The two main approaches for solving RL problems
  - local: unit1/deep-rl
    title: The “Deep” in Deep Reinforcement Learning
  - local: unit1/summary
    title: Summary
  - local: unit1/glossary
    title: Glossary
  - local: unit1/hands-on
    title: Hands-on
  - local: unit1/quiz
    title: Quiz
  - local: unit1/conclusion
    title: Conclusion
  - local: unit1/additional-readings
    title: Additional Readings
- title: Bonus Unit 1. Introduction to Deep Reinforcement Learning with Huggy
  sections:
  - local: unitbonus1/introduction
    title: Introduction
  - local: unitbonus1/how-huggy-works
    title: How Huggy works?
  - local: unitbonus1/train
    title: Train Huggy
  - local: unitbonus1/play
    title: Play with Huggy
  - local: unitbonus1/conclusion
    title: Conclusion
- title: Live 1. How the course work, Q&A, and playing with Huggy
  sections:
  - local: live1/live1
    title: Live 1. How the course work, Q&A, and playing with Huggy 🐶
- title: Unit 2. Introduction to Q-Learning
  sections:
  - local: unit2/introduction
    title: Introduction
  - local: unit2/what-is-rl
    title: What is RL? A short recap
  - local: unit2/two-types-value-based-methods
    title: The two types of value-based methods
  - local: unit2/bellman-equation
    title: The Bellman Equation, simplify our value estimation
  - local: unit2/mc-vs-td
    title: Monte Carlo vs Temporal Difference Learning
  - local: unit2/mid-way-recap
    title: Mid-way Recap
  - local: unit2/mid-way-quiz
    title: Mid-way Quiz
  - local: unit2/q-learning
    title: Introducing Q-Learning
  - local: unit2/q-learning-example
    title: A Q-Learning example
  - local: unit2/q-learning-recap
    title: Q-Learning Recap
  - local: unit2/glossary
    title: Glossary
  - local: unit2/hands-on
    title: Hands-on
  - local: unit2/quiz2
    title: Q-Learning Quiz
  - local: unit2/conclusion
    title: Conclusion
  - local: unit2/additional-readings
    title: Additional Readings
- title: Unit 3. Deep Q-Learning with Atari Games
  sections:
  - local: unit3/introduction
    title: Introduction
  - local: unit3/from-q-to-dqn
    title: From Q-Learning to Deep Q-Learning
  - local: unit3/deep-q-network
    title: The Deep Q-Network (DQN)
  - local: unit3/deep-q-algorithm
    title: The Deep Q Algorithm
  - local: unit3/glossary
    title: Glossary
  - local: unit3/hands-on
    title: Hands-on
  - local: unit3/quiz
    title: Quiz
  - local: unit3/conclusion
    title: Conclusion
  - local: unit3/additional-readings
    title: Additional Readings
- title: Bonus Unit 2. Automatic Hyperparameter Tuning with Optuna
  sections:
  - local: unitbonus2/introduction
    title: Introduction
  - local: unitbonus2/optuna
    title: Optuna
  - local: unitbonus2/hands-on
    title: Hands-on
- title: Unit 4. Policy Gradient with PyTorch
  sections:
  - local: unit4/introduction
    title: Introduction
  - local: unit4/what-are-policy-based-methods
    title: What are the policy-based methods?
  - local: unit4/advantages-disadvantages
    title: The advantages and disadvantages of policy-gradient methods
  - local: unit4/policy-gradient
    title: Diving deeper into policy-gradient
  - local: unit4/pg-theorem
    title: (Optional) the Policy Gradient Theorem
  - local: unit4/glossary
    title: Glossary
  - local: unit4/hands-on
    title: Hands-on
  - local: unit4/quiz
    title: Quiz
  - local: unit4/conclusion
    title: Conclusion
  - local: unit4/additional-readings
    title: Additional Readings
- title: Unit 5. Introduction to Unity ML-Agents
  sections:
  - local: unit5/introduction
    title: Introduction
  - local: unit5/how-mlagents-works
    title: How ML-Agents works?
  - local: unit5/snowball-target
    title: The SnowballTarget environment
  - local: unit5/pyramids
    title: The Pyramids environment
  - local: unit5/curiosity
    title: (Optional) What is curiosity in Deep Reinforcement Learning?
  - local: unit5/hands-on
    title: Hands-on
  - local: unit5/bonus
    title: Bonus. Learn to create your own environments with Unity and MLAgents
  - local: unit5/quiz
    title: Quiz
  - local: unit5/conclusion
    title: Conclusion
- title: Unit 6. Actor Critic methods with Robotics environments
  sections:
  - local: unit6/introduction
    title: Introduction
  - local: unit6/variance-problem
    title: The Problem of Variance in Reinforce
  - local: unit6/advantage-actor-critic
    title: Advantage Actor Critic (A2C)
  - local: unit6/hands-on
    title: Advantage Actor Critic (A2C) using Robotics Simulations with Panda-Gym 🤖
  - local: unit6/quiz
    title: Quiz
  - local: unit6/conclusion
    title: Conclusion
  - local: unit6/additional-readings
    title: Additional Readings
- title: Unit 7. Introduction to Multi-Agents and AI vs AI
  sections:
  - local: unit7/introduction
    title: Introduction
  - local: unit7/introduction-to-marl
    title: An introduction to Multi-Agents Reinforcement Learning (MARL)
  - local: unit7/multi-agent-setting
    title: Designing Multi-Agents systems
  - local: unit7/self-play
    title: Self-Play
  - local: unit7/hands-on
    title: Let's train our soccer team to beat your classmates' teams (AI vs. AI)
  - local: unit7/quiz
    title: Quiz
  - local: unit7/conclusion
    title: Conclusion
  - local: unit7/additional-readings
    title: Additional Readings
- title: Unit 8. Part 1 Proximal Policy Optimization (PPO)
  sections:
  - local: unit8/introduction
    title: Introduction
  - local: unit8/intuition-behind-ppo
    title: The intuition behind PPO
  - local: unit8/clipped-surrogate-objective
    title: Introducing the Clipped Surrogate Objective Function
  - local: unit8/visualize
    title: Visualize the Clipped Surrogate Objective Function
  - local: unit8/hands-on-cleanrl
    title: PPO with CleanRL
  - local: unit8/conclusion
    title: Conclusion
  - local: unit8/additional-readings
    title: Additional Readings
- title: Unit 8. Part 2 Proximal Policy Optimization (PPO) with Doom
  sections:
  - local: unit8/introduction-sf
    title: Introduction
  - local: unit8/hands-on-sf
    title: PPO with Sample Factory and Doom
  - local: unit8/conclusion-sf
    title: Conclusion
- title: Bonus Unit 3. Advanced Topics in Reinforcement Learning
  sections:
  - local: unitbonus3/introduction
    title: Introduction
  - local: unitbonus3/model-based
    title: Model-Based Reinforcement Learning
  - local: unitbonus3/offline-online
    title: Offline vs. Online Reinforcement Learning
  - local: unitbonus3/generalisation
    title: Generalisation Reinforcement Learning
  - local: unitbonus3/rlhf
    title: Reinforcement Learning from Human Feedback
  - local: unitbonus3/decision-transformers
    title: Decision Transformers and Offline RL
  - local: unitbonus3/language-models
    title: Language models in RL
  - local: unitbonus3/curriculum-learning
    title: (Automatic) Curriculum Learning for RL
  - local: unitbonus3/envs-to-try
    title: Interesting environments to try
  - local: unitbonus3/learning-agents
    title: An introduction to Unreal Learning Agents
  - local: unitbonus3/godotrl
    title: An Introduction to Godot RL
  - local: unitbonus3/student-works
    title: Students projects
  - local: unitbonus3/rl-documentation
    title: Brief introduction to RL documentation
- title: Bonus Unit 5. Imitation Learning with Godot RL Agents
  sections:
  - local: unitbonus5/introduction
    title: Introduction
  - local: unitbonus5/the-environment
    title: The environment
  - local: unitbonus5/getting-started
    title: Getting started
  - local: unitbonus5/train-our-robot
    title: Train our robot
  - local: unitbonus5/customize-the-environment
    title: (Optional) Customize the environment
  - local: unitbonus5/conclusion
    title: Conclusion
- title: Certification and congratulations
  sections:
  - local: communication/conclusion
    title: Congratulations
  - local: communication/certification
    title: Get your certificate of completion