The Machine Learning/Reinforcement Learning Reading Group covers topics from several fields, including:

• Supervised/Unsupervised Learning
• Reinforcement Learning
• Bayesian Optimisation

Meetings are designed to be accessible for PhD students with an interest (but not necessarily a specialism) in these areas, providing a relaxed environment in which there are no 'stupid' questions! Indeed, attendees frequently preface their contributions with "I should probably know this, but..."

Topics covered in meetings range from high-level introductions for non-specialists to in-depth analyses of state-of-the-art papers. There is also the opportunity to hear about and learn from each other's research, and to throw problems out to the floor to crowdsource ideas.

Meetings (usually) take place on Thursdays at 11 on Teams (until University re-opens). If you are interested in joining the reading group, please email george.watkins@warwick.ac.uk to confirm the details of the next meeting.

Meetings (by category):

• Supervised/Unsupervised Learning
  • Convolutional Neural Networks - Matt MacPhersonLink opens in a new window
  • Variational Auto-EncodersLink opens in a new window - George WatkinsLink opens in a new window/Matt MacPhersonLink opens in a new window
  • Loss functionsLink opens in a new window - George WatkinsLink opens in a new window
  • Optimization FunctionsLink opens in a new window - George WatkinsLink opens in a new window
  • NLP ClassificationLink opens in a new window - Yuanyi ZhuLink opens in a new window
• Reinforcement Learning
  • Introduction to Reinforcement LearningLink opens in a new window - Charlotte RomanLink opens in a new window
  • Deep Reinforcement LearningLink opens in a new window - George WatkinsLink opens in a new window
  • Reinforcement Learning ApproachesLink opens in a new window - George WatkinsLink opens in a new window
  • Policy Gradient MethodsLink opens in a new window - George WatkinsLink opens in a new window
• Bayesian Optimisation
  • Introduction to Bayesian OptimisationLink opens in a new window - Juan UngreddaLink opens in a new window
• Miscellaneous
  • The ABCs of Approximate Bayesian ComputationLink opens in a new window - Charlie PilgrimLink opens in a new window