In 2016, Lee Sedol, the world’s most recognized Go player was asked what he took from his experience of playing against AlphaGo, one of DeepMind’s many Reinforcement learning (RL) based initiatives including AlphaZero (for Chess), AlphaStar (for StarCraft), etc. said – “I have grown through the experience and understood the reason I play this game”. Experiencing profound humane emotions against a faceless, artificially driven, inanimate opponent, creative in dimensions different than what humans can perceive has ubiquitously changed the way we interact and exchange information. RL and in general AI field have grown exponentially since then. It’s evident that RL has a lot of potential to solve some of the most difficult and nagging problems in the world. It can and will impact people from all walks of life, from business revenue, government policy to climate change.
In this talk, you will learn reinforcement learning starting from basic algorithms to applications
in various domains such as,
- AlphaGo/AlphaStar – Board and Video Games
- AlphaFold – New protien structures
- Energy and Sorting Optimization
- Chip Designs in VLSI
- RLHF – ChatGPT, Conversational Systems
This would be a beginner-friendly talk, Join us to not just understand the RL algorithms but to
see the fascinating impact that it can and will leave on the world.
