Robin Ranjit Singh Chauhan

Robin Ranjit Singh Chauhan

๐ŸŒฑ Head of Eng @AgFunder ๐Ÿง  AI:Reinforcement Learning/ML/DL/NLP๐ŸŽ™๏ธHost @TalkRLPodcast ๐Ÿ’ณ ex-@Microsoft ecomm PgmMgr ๐Ÿค– @UWaterloo CompEng ๐Ÿ‡จ๐Ÿ‡ฆ ๐Ÿ‡ฎ๐Ÿ‡ณ

Appears in 42 Episodes

Danijar Hafner

Danijar Hafner takes us on an odyssey through deep learning & neuroscience, PlaNet, Dreamer, world models, latent dynamics, curious agents, and more!

Csaba Szepesvari

Csaba Szepesvari of DeepMind shares his views on Bandits, Adversaries, PUCT in AlphaGo / AlphaZero / MuZero, AGI and RL, what is timeless, and more!

Ben Eysenbach

Ben Eysenbach schools us on human supervision, SORB, DIAYN, techniques for exploration, teaching RL, virtual conferences, and much more!

NeurIPS 2019 Deep RL Workshop

Hear directly from presenters at the NeurIPS 2019 Deep RL Workshop on their work!

Scott Fujimoto

Scott Fujimoto expounds on his TD3 and BCQ algorithms, DDPG, Benchmarking Batch RL, and more!

Jessica Hamrick

Jessica Hamrick sheds light on Model-based RL, Structured agents, Mental simulation, Metacontrol, Construction environments, Blueberries, and more!

Pablo Samuel Castro

Pablo Samuel Castro drops in and drops knowledge on distributional RL, bisimulation, the Dopamine RL Framework, TF-Agents, and much more!

Kamyar Azizzadenesheli

Kamyar Azizzadenesheli brings us insight on Bayesian RL, Generative Adversarial Tree search, what goes into great RL papers, and much more!

Antonin Raffin and Ashley Hill

Antonin Raffin and Ashley Hill discuss Stable Baselines past, present and future, State Representation Learning, S-RL Toolbox, RL on real robots, big compute for RL an...

Michael Littman

ACM Fellow Professor Michael L Littman enlightens us on Human feedback in RL, his Udacity courses, Theory of Mind, organizing the RLDM Conference, RL past and present,...

Natasha Jaques

Natasha Jaques talks about her PhD, her papers on Social Influence in Multi-Agent RL, ML & Climate Change, Sequential Social Dilemmas, internships at DeepMind and Goog...

About TalkRL Podcast: All Reinforcement Learning, All the Time

Introducing TalkRL Podcast! Also check out our website at talkRL.com

Broadcast by