Reinforcement Learning (RL) has been a key part of the huge growth and advances in AI over recent years. Combined with deep neural networks, RL has enabled Google Deepmind's DQG to play Atari games, and was a key part of the AlphaGo system that mastered the notoriously difficult 3000-year old game of Go. Google Deepmind's blog on their RL advances: https://deepmind.com/blog/deep-reinforcement-learning/
We're lucky to have Ali Chaudhry, who is doing PhD research in RL, lead an introductory session:
gently introducing the basics of Reinforcement Learning
showing how Reinforcement Learning combined with neural networks has overcome key machine learning challenges and led to recent advances in AI
exploring some creative applications of reinforcement learning algorithms
You don't need to be an expert to benefit from this session. Beginners will gain an intuitive understanding of reinforcement learning, and understand enough of the detail to be able implement reinforcement learning yourself.
The session will start at 7.00pm and you can arrive from 6.30pm. Complimentary tea and coffee is available in the bar area.
YOU MAY ALSO LIKE:
- Meta Reinforcement Learning: The Power of Generalizing RL Algorithms (SkillsCast recorded in July 2019)
- Ceci n’est pas un canard – Machine Learning and Generative Adversarial Networks (Online Meetup on 6th August 2020)
- Digital Discrimination: Cognitive Bias in Machine Learning (SkillsCast recorded in June 2020)
- Using A.I. to Help Humanitarian Causes (SkillsCast recorded in May 2020)
Reinforcement Learning & Creative Applications
Ali is a self-taught programmer, currently doing a PhD in Artificial Intelligence and Education at University College London. His research focuses on applying human-centered learning science theories on Deep Reinforcement Learning algorithms. These days he's obsessed with GANs and Variational Autoencoders.