Published Oct 14, 2021
Advancing Deep Reinforcement Learning with NetHack, w/ Tim Rocktäschel - #527
Dive into the complexities of deep reinforcement learning with Tim Rocktäschel as he reveals how NetHack serves as a challenging training ground for AI agents, emphasizing the importance of generalization, intrinsic motivation, and innovative unsupervised environment design through frameworks like MiniHack.
Topics covered
Popular Clips
Episode Highlights
Related Episodes
Deep Reinforcement Learning for Game Testing at EA with Konrad Tollmar - #517
Answers 383 questions
Reinforcement Learning Deep Dive with Pieter Abbeel - #28
Answers 383 questions
Hierarchical and Continual RL with Doina Precup - #567
Answers 383 questions
Advancements in Machine Learning with Sergey Levine - #355
Answers 383 questions
Reinforcement Learning: The Next Frontier of Gaming with Danny Lange - #24
Answers 383 questions
Upside-Down Reinforcement Learning with Jürgen Schmidhuber - #357
Answers 383 questions
Training Large-Scale Deep Nets with RL with Nando de Freitas - TWiML Talk #213
Answers 383 questions
Knowledge Graphs and Expert Augmentation with Marisa Boston - TWiML Talk #204
Answers 383 questions
Trends in Reinforcement Learning with Simon Osindero - TWiML Talk #217
Answers 383 questions
Towards Abstract Robotic Understanding with Raja Chatila - #118
Answers 383 questions
