Reinforcement Learning - Developing Self-Learning Models
summary
Reinforcement learning is presented as a way for AI systems to train themselves by exploring solutions to complex problems; the talk explains the core concepts and new application areas. Jörg Neumann and Robin Müller outline how to develop and deploy reinforcement-learning models sensibly, covering practical guidance for building and using these self-learning systems.
AI-written summary · about
chapters (6)
- 0:00RL intro
- 5:00Classic ML differences
- 16:51RL fundamentals
- 25:28Flappy Bird Q-Learning
- 33:20Deep RL for complex tasks
- 35:05Summary
related talks
02mDesigning a Video Game AI
13mReinforcement learning and it's growing role in AI
31mDesigning game AI with reinforcement learning
49mReinforcement Learning: Demystifying the hype
35mIndustrial Applications of Reinforcement Learning
06mRL in real life: Bringing reinforcement learning to the enterprise
30mReinforcement Learning - ChatGPT, Playing Games & More
44mReinforcement learning: A gentle introduction