Tim & Heinrich — Democraticizing Reinforcement Learning Research
Tim & Heinrich — Democraticizing Reinforcement Learning Research  
Podcast: Gradient Dissent: Conversations on AI
Published On: Thu Mar 04 2021
Description: Since reinforcement learning requires hefty compute resources, it can be tough to keep up without a serious budget of your own. Find out how the team at Facebook AI Research (FAIR) is looking to increase access and level the playing field with the help of NetHack, an archaic rogue-like video game from the late 80s.Links discussed:The NetHack Learning Environment: https://ai.facebook.com/blog/nethack-learning-environment-to-advance-deep-reinforcement-learning/Reinforcement learning, intrinsic motivation: https://arxiv.org/abs/2002.12292Knowledge transfer:https://arxiv.org/abs/1910.08210Tim Rocktäschel is a Research Scientist at Facebook AI Research (FAIR) London and a Lecturer in the Department of Computer Science at University College London (UCL). At UCL, he is a member of the UCL Centre for Artificial Intelligence and the UCL Natural Language Processing group. Prior to that, he was a Postdoctoral Researcher in the Whiteson Research Lab, a Stipendiary Lecturer in Computer Science at Hertford College, and a Junior Research Fellow in Computer Science at Jesus College, at the University of Oxford.https://twitter.com/_rocktHeinrich Kuttler is an AI and machine learning researcher at Facebook AI Research (FAIR) and before that was a research engineer and team lead at DeepMind.https://twitter.com/HeinrichKuttlerhttps://www.linkedin.com/in/heinrich-kuttler/Topics covered:0:00 a lack of reproducibility in RL1:05 What is NetHack and how did the idea come to be?5:46 RL in Go vs NetHack11:04 performance of vanilla agents, what do you optimize for18:36 transferring domain knowledge, source diving22:27 human vs machines intrinsic learning28:19 ICLR paper - exploration and RL strategies35:48 the future of reinforcement learning43:18 going from supervised to reinforcement learning45:07 reproducibility in RL50:05 most underrated aspect of ML, biggest challenges?Get our podcast on these other platforms:Apple Podcasts: http://wandb.me/apple-podcastsSpotify: http://wandb.me/spotifyGoogle: http://wandb.me/google-podcastsYouTube: http://wandb.me/youtubeSoundcloud: http://wandb.me/soundcloudTune in to our bi-weekly virtual salon and listen to industry leaders and researchers in machine learning share their research:http://wandb.me/salonJoin our community of ML practitioners where we host AMA's, share interesting projects and meet other people working in Deep Learning:http://wandb.me/slackOur gallery features curated machine learning reports by researchers exploring deep learning techniques, Kagglers showcasing winning models, and industry leaders sharing best practices:https://wandb.ai/gallery