Researchers from Google DeepMind have collaborated with the University College London (UCL) to offer students a comprehensive introduction to modern reinforcement learning.
The series comprises 13 lectures covering the fundamentals of reinforcement learning and planning in sequential decision problems before progressing to more advanced topics and modern deep RL algorithms. DeepMind Research Scientists and Engineers Hado van Hasselt, Diana Borsa, and Matteo Hessel lead a 13-part self-contained introduction to RL and deep RL, aimed at students at Master’s level and above.
The 13 lecture series includes:
- Introduction to Reinforcement Learning
- Exploration & Control
- MDPs & Dynamic Programming
- Theoretical Fundamentals of Dynamic Programming Algorithms
- Model-free Prediction
- Model-free Control
- Function Approximation
- Planning & models
- Policy-Gradient & Actor-Critic methods
- Approximate Dynamic Programming
- Multi-step & Off Policy
- Deep Reinforcement Learning #1
- Deep Reinforcement Learning #2
The programme is designed with an aim to give students a detailed understanding of various topics, including Markov Decision Processes, sample-based learning algorithms (e.g. (double) Q-learning, SARSA), deep reinforcement learning, and more. It also explores more advanced topics like off-policy learning, multi-step updates and eligibility traces, as well as conceptual and practical considerations in implementing deep reinforcement learning algorithms such as rainbow DQN.
In a recent set of events, the Alphabet-owned research lab DeepMind announced that it is making AlphaFold 2.0 source code public. This AI-based algorithm predicts the shape of proteins, a major challenge in the healthcare and life sciences field. With this decision, DeepMind hopes to offer easy access and better research opportunities to the scientific community in areas such as drug discovery.