Article Source

• Title: Deep RL Bootcamp

Deep RL Bootcamp

• Core Lecture 1 Intro to MDPs and Exact Solution Methods – Pieter Abbeel (videoslides)
• Core Lecture 2 Sample-based Approximations and Fitted Learning – Rocky Duan (videoslides)
• Core Lecture 3 DQN + Variants – Vlad Mnih (videoslides)
• Core Lecture 4a Policy Gradients and Actor Critic – Pieter Abbeel (videoslides)
• Core Lecture 4b Pong from Pixels – Andrej Karpathy (videoslides)
• Core Lecture 5 Natural Policy Gradients, TRPO, and PPO – John Schulman (videoslides)
• Core Lecture 6 Nuts and Bolts of Deep RL Experimentation – John Schulman (videoslides)
• Core Lecture 7 SVG, DDPG, and Stochastic Computation Graphs – John Schulman (videoslides)
• Core Lecture 8 Derivative-free Methods – Peter Chen (videoslides)
• Core Lecture 9 Model-based RL – Chelsea Finn (videoslides)
• Core Lecture 10a Utilities – Pieter Abbeel (videoslides)
• Core Lecture 10b Inverse RL – Chelsea Finn (videoslides)
• Frontiers Lecture I: Recent Advances, Frontiers and Future of Deep RL – Vlad Mnih (videoslides)
• Frontiers Lecture II: Recent Advances, Frontiers and Future of Deep RL – Sergey Levine (videoslides)
• TAs Research Overviews (videoslides)