# wangshusen/drl

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/wangshusen-drl).**

4,512 stars · 669 forks · other

## Links

- GitHub: https://github.com/wangshusen/DRL
- awesome-repositories: https://awesome-repositories.com/repository/wangshusen-drl.md

## Description

DRL is a curated educational resource that teaches deep reinforcement learning through a structured series of lectures and videos. It covers the three main families of reinforcement learning methods: actor-critic architectures, value-based algorithms like Q-learning and DQN, and policy-based techniques that directly optimize an agent's action-selection strategy.

The curriculum extends beyond these core topics to include imitation learning, multi-agent training, and methods for handling continuous action spaces. Content is organized as markdown-driven documentation that generates static, navigable pages, creating a clear learning path through the mathematical foundations and practical algorithms of reinforcement learning.

## Tags

### Education & Learning Resources

- [Reinforcement Learning Curricula](https://awesome-repositories.com/f/education-learning-resources/deep-learning-curriculum/reinforcement-learning-curricula.md) — Provides a structured educational resource teaching the mathematical foundations of reinforcement learning.
- [Lecture Sequences](https://awesome-repositories.com/f/education-learning-resources/educational-resources/reference-and-media/tutorials-media-curated-lists/interactive-learning-media/video-learning-channels/video-lectures/lecture-sequences.md) — Organizes educational content as a structured sequence of lectures and videos for progressive learning.
- [Reinforcement Learning Theory](https://awesome-repositories.com/f/education-learning-resources/reinforcement-learning-theory.md) — Teaches the mathematical foundations and algorithms of reinforcement learning through structured lectures.

### Artificial Intelligence & ML

- [Actor-Critic Architectures](https://awesome-repositories.com/f/artificial-intelligence-ml/actor-critic-architectures.md) — Teaches actor-critic architectures that combine policy and value learning for stable training.
- [Deep Learning Policy Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/deep-learning-policy-frameworks.md) — Explains policy gradient techniques that directly optimize an agent's action-selection strategy.
- [Deep Q-Learning Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/deep-q-learning-frameworks.md) — Teaches algorithms that learn action values to derive optimal policies through Q-learning and DQN.
- [Policy Gradient Methods](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/machine-learning-training/utilities/gradient-optimization-techniques/policy-gradient-methods.md) — Provides a structured tutorial series explaining policy gradient techniques for directly optimizing action-selection strategies.
- [Reinforcement Learning Value Estimators](https://awesome-repositories.com/f/artificial-intelligence-ml/reinforcement-learning-value-estimators.md) — Teaches algorithms like Q-learning and DQN that learn action values to derive optimal policies.
- [Value-Based Methods Tutorials](https://awesome-repositories.com/f/artificial-intelligence-ml/reinforcement-learning-value-estimators/value-based-methods-tutorials.md) — Ships a dedicated curriculum covering Q-learning and DQN algorithms for learning action values.
- [Continuous Action Space Tutorials](https://awesome-repositories.com/f/artificial-intelligence-ml/continuous-control-training/continuous-action-space-tutorials.md) — Teaches how to handle environments with real-valued actions by extending policy gradient methods. ([source](https://cdn.jsdelivr.net/gh/wangshusen/drl@master/README.md))
- [Expert Imitation Learning](https://awesome-repositories.com/f/artificial-intelligence-ml/expert-imitation-learning.md) — Teaches imitation learning approaches that copy expert behavior instead of learning from trial and error. ([source](https://cdn.jsdelivr.net/gh/wangshusen/drl@master/README.md))
- [Multi-Agent Training](https://awesome-repositories.com/f/artificial-intelligence-ml/reinforcement-learning-training/multi-agent-training.md) — Addresses the unique challenges of environments where several learning agents interact simultaneously. ([source](https://cdn.jsdelivr.net/gh/wangshusen/drl@master/README.md))