All Episodes

Displaying episodes 1 - 30 of 52 in total

Arash Ahmadian on Rethinking RLHF

Arash Ahmadian is a Researcher at Cohere and Cohere For AI focussed on Preference Training of large language models. He’s also a researcher at the Vector Institute of ...

Glen Berseth on RL Conference

Glen Berseth is an assistant professor at the Université de Montréal, a core academic member of the Mila - Quebec AI Institute, a Canada CIFAR AI chair, member l'Insti...

Ian Osband

Ian Osband is a Research scientist at OpenAI (ex DeepMind, Stanford) working on decision making under uncertainty.  We spoke about: - Information theory and RL - Explo...

Sharath Chandra Raparthy

Sharath Chandra Raparthy on In-Context Learning for Sequential Decision Tasks, GFlowNets, and more!  Sharath Chandra Raparthy is an AI Resident at FAIR at Meta, and di...

Pierluca D'Oro and Martin Klissarov

Pierluca D'Oro and Martin Klissarov on Motif and RLAIF, Noisy Neighborhoods and Return Landscapes, and more!  Pierluca D'Oro is PhD student at Mila and visiting resear...

Martin Riedmiller

Martin Riedmiller of Google DeepMind on controlling nuclear fusion plasma in a tokamak with RL, the original Deep Q-Network, Neural Fitted Q-Iteration, Collect and Inf...

Max Schwarzer

Max Schwarzer is a PhD student at Mila, with Aaron Courville and Marc Bellemare, interested in RL scaling, representation learning for RL, and RL for science.  Max spe...

Julian Togelius

Julian Togelius is an Associate Professor of Computer Science and Engineering at NYU, and Cofounder and research director at modl.ai  Featured References  Choose Your ...

Jakob Foerster

Jakob Foerster on Multi-Agent learning, Cooperation vs Competition, Emergent Communication, Zero-shot coordination, Opponent Shaping, agents for Hanabi and Prisoner's ...

Danijar Hafner 2

Danijar Hafner on the DreamerV3 agent and world models, the Director agent and heirarchical RL,  realtime RL on robots with DayDreamer, and his framework for unsupervi...

Jeff Clune

AI Generating Algos, Learning to play Minecraft with Video PreTraining (VPT), Go-Explore for hard exploration, POET and Open Endedness, AI-GAs and ChatGPT, AGI predict...

Natasha Jaques 2

Hear about why OpenAI cites her work in RLHF and dialog models, approaches to rewards in RLHF, ChatGPT, Industry vs Academia, PsiPhi-Learning, AGI and more!  Dr Natash...

Jacob Beck and Risto Vuorio

Jacob Beck and Risto Vuorio on their recent Survey of Meta-Reinforcement Learning.  Jacob and Risto are Ph.D. students at Whiteson Research Lab at University of Oxford...

John Schulman

John Schulman, OpenAI cofounder and researcher, inventor of PPO/TRPO talks RL from human feedback, tuning GPT-3 to follow instructions (InstructGPT) and answer long-fo...

Sven Mika

Sven Mika of Anyscale on RLlib present and future, Ray and Ray Summit 2022, applied RL in Games / Finance / RecSys, and more!

Karol Hausman and Fei Xia

Karol Hausman and Fei Xia of Google Research on newly updated (PaLM-)SayCan, Inner Monologue, robot learning, combining robotics with language models, and more!

Sai Krishna Gottipati

Sai Krishna Gottipati of AI Redefined on RL for synthesizable drug discovery, Multi-Teacher Self-Play, Cogment framework for realtime multi-actor RL, AI + Chess, and m...

Aravind Srinivas 2

Aravind Srinivas, Research Scientist at OpenAI, returns to talk Decision Transformer, VideoGPT, choosing problems, and explore vs exploit in research careers

Rohin Shah

DeepMind Research Scientist Dr. Rohin Shah on Value Alignment, Learning from Human feedback, Assistance paradigm, the BASALT MineRL competition, his Alignment Newslett...

Jordan Terry

Jordan Terry on maintaining Gym and PettingZoo, hardware accelerated environments and the future of RL, environment models for multi-agent RL, and more!

Robert Lange

Robert Lange on learning vs hard-coding, meta-RL, Lottery Tickets and Minimal Task Representations, Action Grammars and more!

NeurIPS 2021 Political Economy of Reinforcement Learning Systems (PERLS) Workshop

Dr. Thomas Gilbert and Dr. Mark Nitzberg on the upcoming PERLS Workshop @ NeurIPS 2021

Amy Zhang

Amy Zhang shares her work on Invariant Causal Prediction for Block MDPs, Multi-Task Reinforcement Learning with Context-based Representations, MBRL-Lib, shares insight...

Xianyuan Zhan

Xianyuan Zhan on DeepThermal for controlling thermal power plants, the MORE algorithm for Model-based Offline RL, comparing AI in China and the US, and more!

Eugene Vinitsky

Eugene Vinitsky of UC Berkeley on social norms and sanctions, traffic simulation, mixed-autonomy traffic, and more!

Jess Whittlestone

Jess Whittlestone on societal implications of deep reinforcement Learning, AI policy, warning signs of transformative progress in AI, and more!

Aleksandra Faust

Aleksandra Faust of Google Brain Research on AutoRL, meta-RL, learning to learn & learning to teach, curriculum learning, collaborations between senior and junior rese...

Sam Ritter

Sam Ritter of DeepMind on Neuroscience and RL, Episodic Memory, Meta-RL, Synthetic Returns, the MERLIN agent, decoding brain activation, and more!

Thomas Krendl Gilbert

Thomas Krendl Gilbert on the Political Economy of Reinforcement Learning Systems & Autonomous Vehicles, Sociotechnical Commitments, AI Development for the Public Inter...

Marc G. Bellemare

Marc G. Bellemare shares insight on his work including Deep Q-Networks, Distributional RL, Project Loon and RL in the Stratosphere, the origins of the Arcade Learning ...

Broadcast by