Ankur Narang: Senior Vice President – Technology & Decision Sciences at Yatra at Cypher2017- Part3/3
summary
Covers the development and recent advances in Deep Reinforcement Learning (DRL), explaining how techniques from deep learning and reinforcement learning enabled successes like AlphaGo and applications in robotics, NLP/machine translation, vision, finance, healthcare and intelligent transportation. Describes use cases (games, robotics, finance), discusses combining DRL with search and planning, and highlights remaining challenges around sample efficiency, generalisation, interpretability and steps toward general-purpose AGI.
AI-written summary · about
related talks
05mPractical insights into deep reinforcement learning
49mReinforcement Learning: Demystifying the hype
01h 17mTraining intelligent game agents using deep reinforcement learning
01h 03mIEEE CoG 2019 - Industry Day - David Silver (DeepMind)
30mReinforcement Learning - ChatGPT, Playing Games & More
43mIntroduction to (deep) reinforcement learning
31mDesigning game AI with reinforcement learning
47mAdvanced Reinforcement Learning & Data Science for Social Impact