Advanced Deep Learning and Reinforcement Learning at UCL & DeepMind
Please install Open in Colab extension in Google Chrome in order to open a Github-hosted notebook in Google Colab with one-click.
The course is taught in collaboration with DeepMind. The majority of lectures will be taught by guest lecturers from DeepMind who are leading experts in the field of machine learning and will teach about topics in which they are specialised.
This repo contains homework, exams and slides I collected from internet without solutions. This repo is only for students / developers who are interested in this topic. If this repo conflicts your rights, please do not hesitate to contact me. I promise I will delete this (both repo and history) ASAP.
Overview
This course, taught originally at UCL and recorded for online access, has two interleaved parts that converge towards the end of the course. One part is on machine learning with deep neural networks, the other part is about prediction and control using reinforcement learning. The two strands come together when we discuss deep reinforcement learning, where deep neural networks are trained as function approximators in a reinforcement learning setting.
- The deep learning stream of the course will cover a short introduction to neural networks and supervised learning with TensorFlow, followed by lectures on convolutional neural networks, recurrent neural networks, end-to-end and energy-based learning, optimization methods, unsupervised learning as well as attention and memory. Possible applications areas to be discussed include object recognition and natural language processing.
- The reinforcement learning stream will cover Markov decision processes, planning by dynamic programming, model-free prediction and control, value function approximation, policy gradient methods, integration of learning and planning, and the exploration/exploitation dilemma. Possible applications to be discussed include learning to play classic board games as well as video games.
Lecture videos
| Lecture | Youtube link |
|---|---|
| Deep Learning 1: Introduction to Machine Learning Based AI | lecture video |
| Deep Learning 2: Introduction to TensorFlow | lecture video |
| Deep Learning 3: Neural Networks Foundations | lecture video |
| Reinforcement Learning 1: Introduction to Reinforcement Learning | lecture video |
| Reinforcement Learning 2: Exploration and Exploitation | lecture video |
| Reinforcement Learning 3: Markov Decision Processes and Dynamic Programming | lecture video |
| Reinforcement Learning 4: Model-Free Prediction and Control | lecture video |
| Deep Learning 4: Beyond Image Recognition, End-to-End Learning, Embeddings | lecture video |
| Reinforcement Learning 5: Function Approximation and Deep Reinforcement Learning | lecture video |
| Reinforcement Learning 6: Policy Gradients and Actor Critics | lecture video |
| Deep Learning 5: Optimization for Machine Learning | lecture video |
| Reinforcement Learning 7: Planning and Models | lecture video |
| Deep Learning 6: Deep Learning for NLP | lecture video |
| Reinforcement Learning 8: Advanced Topics in Deep RL | lecture video |
| Deep Learning 7. Attention and Memory in Deep Learning | lecture video |
| Reinforcement Learning 9: A Brief Tour of Deep RL Agents | lecture video |
| Deep Learning 8: Unsupervised learning and generative models | lecture video |
| Reinforcement Learning 10: Classic Games Case Study | lecture video |
Textbooks
[1] Richard S. Sutton, Andrew G. Barto. "Reinforcement learning: an introduction". 1998.
[2] Csaba Szepesvรกri. "Algorithms for reinforcement learning". 2010.
[3] Ian Goodfellow, Yoshua Bengio, Aaron Courville. "Deep learning". 2016.