ICARL

@UCg2J3fIRTfNUVV8Of-0Cckw - 1.4K subscribers

Imperial College Autonomous Reasoning & Learning Group We host prominent researchers working on topics related to Reasoning and Reinforcement Learning. Co-organized by @borruell and @afspies

Home Videos Live Playlists

SIMA 2: A Generalist Embodied Agent for Virtual Worlds | Jane X. Wang

SIMA 2: A Generalist Embodied Agent for Virtual Worlds | Jane X. Wang ICARL

237 views - 5 months ago

Modern Methods in Embodied AI: Imitation Learning and World Modeling | Tim Pearce

Modern Methods in Embodied AI: Imitation Learning and World Modeling | Tim Pearce ICARL

300 views - 6 months ago

From World Models to World Understanding | Elahe Arani

From World Models to World Understanding | Elahe Arani ICARL

122 views - 6 months ago

Foundation models in biology | Alberto Bégué

Foundation models in biology | Alberto Bégué ICARL

130 views - 10 months ago

Making reasoning machines with reinforcement learning: experiences from the field | Albert Jiang

Making reasoning machines with reinforcement learning: experiences from the field | Albert Jiang ICARL

232 views - 1 year ago

Learning actions, policies, rewards and environments from videos alone | Ashley Edwards

Learning actions, policies, rewards and environments from videos alone | Ashley Edwards ICARL

196 views - 1 year ago

Dynamic Deep Learning | Richard Sutton

Dynamic Deep Learning | Richard Sutton ICARL

20K views - 1 year ago

LLMs as Creativity Support Tool for Live Artistic Performance | Piotr Mirowski

LLMs as Creativity Support Tool for Live Artistic Performance | Piotr Mirowski ICARL

232 views - 1 year ago

Real-world Reinforcement Learning in Multi-Agent Systems | Eugene Vinitsky

Real-world Reinforcement Learning in Multi-Agent Systems | Eugene Vinitsky ICARL

1.4K views - 1 year ago

Exploring the Space of Key-Value-Query Models with Intention | Marta Garnelo

Exploring the Space of Key-Value-Query Models with Intention | Marta Garnelo ICARL

1.1K views - 1 year ago

Genie: Generative Interactive Environments | Jake Bruce

Genie: Generative Interactive Environments | Jake Bruce ICARL

499 views - 1 year ago

Exploring Alternative Bio-Inspired Neural Building Blocks for Fast RL | Sebastian Risi

Exploring Alternative Bio-Inspired Neural Building Blocks for Fast RL | Sebastian Risi ICARL

561 views - 1 year ago

Champion-Level Drone Racing using Deep Reinforcement Learning | Leonard Bauersfeld

Champion-Level Drone Racing using Deep Reinforcement Learning | Leonard Bauersfeld ICARL

1.3K views - 1 year ago

Memory-Enhanced Neural Solvers for Efficient Adaptation in Combinatorial Optim. | Félix Chalumeau

Memory-Enhanced Neural Solvers for Efficient Adaptation in Combinatorial Optim. | Félix Chalumeau ICARL

356 views - 1 year ago

Understanding Incremental Unsupervised Exploration for Goal-based RL | Alessandro Lazaric

Understanding Incremental Unsupervised Exploration for Goal-based RL | Alessandro Lazaric ICARL

251 views - 2 years ago

AlphaDev | Daniel Mankowitz and Andrea Michi

AlphaDev | Daniel Mankowitz and Andrea Michi ICARL

306 views - 2 years ago

Resurrecting Recurrent Neural Networks for Long Sequences | Razvan Pascanu

Resurrecting Recurrent Neural Networks for Long Sequences | Razvan Pascanu ICARL

2K views - 2 years ago

A Comparative Cognition Approach to AI Evaluation | Lucy Cheke

A Comparative Cognition Approach to AI Evaluation | Lucy Cheke ICARL

376 views - 2 years ago

Passive Learning of Active Causal Strategies in Agents and Language Models | Andrew Lampinen

Passive Learning of Active Causal Strategies in Agents and Language Models | Andrew Lampinen ICARL

867 views - 3 years ago

Towards Ad-Hoc Teamwork for Improved Player Experience | Sam Devlin

Towards Ad-Hoc Teamwork for Improved Player Experience | Sam Devlin ICARL

151 views - 3 years ago

How knowing language can make general AI systems smarter | Felix Hill

How knowing language can make general AI systems smarter | Felix Hill ICARL

537 views - 3 years ago

Outracing champion Gran Turismo drivers with Deep Reinforcement Learning | Florian Fuchs

Outracing champion Gran Turismo drivers with Deep Reinforcement Learning | Florian Fuchs ICARL

894 views - 3 years ago

Symmetries in Single and Multi-agent Learning and AI4Science | Elise van der Pol

Symmetries in Single and Multi-agent Learning and AI4Science | Elise van der Pol ICARL

291 views - 3 years ago

The NetHack Learning Environment and Its Challenges for Open-Ended Learning | Tim Rocktäeschel

The NetHack Learning Environment and Its Challenges for Open-Ended Learning | Tim Rocktäeschel ICARL

487 views - 3 years ago

Understanding and Improving Model-Based Deep Reinforcement Learning | Jessica Hamrick

Understanding and Improving Model-Based Deep Reinforcement Learning | Jessica Hamrick ICARL

1.3K views - 3 years ago

High-Dimensional Black-Box Optimisation in Small Data Regimes | Haitham Bou Ammar

High-Dimensional Black-Box Optimisation in Small Data Regimes | Haitham Bou Ammar ICARL

456 views - 3 years ago

Towards Multi-agent Emergent Communication | Angeliki Lazaridou

Towards Multi-agent Emergent Communication | Angeliki Lazaridou ICARL

1K views - 4 years ago

Zero-Shot Coordination and Off-Belief Learning | Jakob Foerster

Zero-Shot Coordination and Off-Belief Learning | Jakob Foerster ICARL

1K views - 4 years ago