Reinforcement learning
Deep Reinforcement Learning in Python
Explore deep reinforcement learning in Python, including A2C, DDPG and evolution strategies.
A small sample of 30,000+ courses curated from around the world, all available to DoJo members.
A free 30-minute conversation with Ted about your goals.
Already a member? Open this course (opens in a new tab)
Course topics
Reinforcement learning
- A2C
- DDPG
- Evolution strategies
You observe the behaviour
Find your fit
Is this a useful starting point?
For learners with reinforcement-learning and MDP knowledge who can build a TensorFlow convolutional network.
- Starting point
- Expert
- Course length
- 8.5 total hours
- Lessons
- 51 lectures
Course by Lazy Programmer Inc., Lazy Programmer Team
Course last updated: 02/2026
Requirements
- Know the basics of MDPs (Markov Decision Processes) and Reinforcement Learning
- Helpful to have seen my first two Reinforcement Learning courses
- Know how to build a convolutional neural network in Tensorflow
What is included
- 8.5 hours on-demand video
- Access on mobile
- Certificate of completion
DoJo membership: A$250 per month per seat, excluding GST. Includes fortnightly group support and a private member community.
Explore the lessons
Course curriculum.
11 sections • 51 lectures • 8h 37m total length
Welcome3 lectures • 16min
- Introduction03:45
- Outline07:46
- Where to get the code04:36
Review of Fundamental Reinforcement Learning Concepts8 lectures • 1hr 20min
- Review Section Introduction04:00
- The Explore-Exploit Dilemma13:34
- Markov Decision Processes (MDPs)20:18
- Monte Carlo Methods07:53
- Temporal Difference Learning (TD)17:16
- OpenAI Gym Warmup06:45
- Review Section Summary07:28
- Suggestion Box03:10
A2C (Advantage Actor-Critic)11 lectures • 1hr 39min
- A2C Section Introduction07:53
- A2C Theory (part 1)20:39
- A2C Theory (part 2)06:47
- A2C Theory (part 3)03:13
- A2C Demo03:08
- A2C Code - Rough Sketch07:10
- Multiple Processes08:46
- Environment Wrappers11:48
- Convolutional Neural Network05:30
- A2C17:21
- A2C Section Summary06:39
DDPG (Deep Deterministic Policy Gradient)7 lectures • 1hr 20min
- DDPG Section Introduction03:36
- Deep Q-Learning (DQN) Review09:20
- DDPG Theory18:41
- MuJoCo18:52
- DDPG Code (part 1)18:30
- DDPG Code (part 2)06:35
- DDPG Section Summary04:24
ES (Evolution Strategies)9 lectures • 1hr 29min
- ES Section Introduction06:25
- ES Theory20:16
- Notes on Evolution Strategies08:49
- ES for Optimizing a Function06:32
- ES for Supervised Learning06:39
- Flappy Bird12:08
- ES for Flappy Bird in Code15:01
- ES for MuJoCo in Code07:49
- ES Section Summary05:01
Quizzes0 lectures • 0min
- A2C Quiz 3 questions
- DDPG Quiz 3 questions
- ES Quiz 3 questions
Appendix / FAQ Intro1 lecture • 4min
- What is the Appendix?03:46
Setting Up Your Environment (FAQ by Student Request)3 lectures • 42min
- Pre-Installation Check04:12
- Anaconda Environment Setup20:20
- How to install Numpy, Scipy, Matplotlib, Pandas, IPython, Theano, and TensorFlow17:30
Extra Help With Python Coding for Beginners (FAQ by Student Request)4 lectures • 42min
- How to Code by Yourself (part 1)15:54
- How to Code by Yourself (part 2)09:23
- Proof that using Jupyter Notebook is the same as not using it12:29
- Python 2 vs Python 304:38
Effective Learning Strategies for Machine Learning (FAQ by Student Request)4 lectures • 1hr
- How to Succeed in this Course (Long Version)10:24
- Is this for Beginners or Experts? Academic or Practical? Fast or slow-paced?22:04
- Machine Learning and AI Prerequisite Roadmap (pt 1)11:18
- Machine Learning and AI Prerequisite Roadmap (pt 2)16:07
Appendix / FAQ Finale1 lecture • 6min
- BONUS05:48
From learning to practice
Try this next.
Compare two reinforcement-learning approaches using the same small learning task.
A useful next step
Choose where to start.
Talk through your goals in a free 30-minute discovery call with Ted. Bring a task you want to improve and the tools you already use.
Book a discovery callExplore DoJo membership