Practical insights into deep reinforcement learning
summary
Covers deep reinforcement learning (DRL), explaining how reinforcement learning uses trial-and-error to optimize long-term goals and how deep learning lets agents learn from raw sensor inputs like images without manual feature engineering. Discusses the role of cloud-based, scalable compute in making DRL more accessible for applications in robotics, automation, and operations research.
AI-written summary · about
chapters (4)
related talks
49mReinforcement Learning: Demystifying the hype
01h 17mTraining intelligent game agents using deep reinforcement learning
43mIntroduction to (deep) reinforcement learning
26mAnkur Narang; Senior Vice President – Technology & Decision Sciences at Yatra at Cypher2017- Part1/3
01h 35mDeep Robotic Learning
17mAnkur Narang: Senior Vice President – Technology & Decision Sciences at Yatra at Cypher2017- Part3/3
35mIndustrial Applications of Reinforcement Learning
28mDeep Reinforcement Learning: theory, intuition, code