UCL Deciding, Acting, and Reasoning with Knowledge (DARK) Lab is a research group at the UCL Centre for Artificial Intelligence focusing on Reinforcement Learning and Deep Learning.

For more information about UCL DARK Lab, visit our website: dark.cs.ucl.ac.uk

Martin Klissarov - MaestroMotif: Skill Design from AI Feedback
40:55
Martin Klissarov - MaestroMotif: Skill Design from AI Feedback
Anssi Kanervisto - After 8 years, Minecraft continues to push the frontier of AI
41:37
Anssi Kanervisto - After 8 years, Minecraft continues to push the frontier of AI
Adam Gleave - Adversarial Robustness of Superhuman AI Systems
1:06:06
Adam Gleave - Adversarial Robustness of Superhuman AI Systems
Maciej and Bartek - Fine-tuning Reinforcement Learning Models is a Forgetting Mitigation Problem
47:52
Maciej and Bartek - Fine-tuning Reinforcement Learning Models is a Forgetting Mitigation Problem
Jacob Andreas - Toward Natural Language Supervision
1:03:24
Jacob Andreas - Toward Natural Language Supervision
DeepMind Open-Endedness Team - Genie: Generative Interactive Environments
39:26
DeepMind Open-Endedness Team - Genie: Generative Interactive Environments
Stefano V. Albrecht - From Deep Reinforcement Learning to LLM-based Agents
44:34
Stefano V. Albrecht - From Deep Reinforcement Learning to LLM-based Agents
Louis Kirsch - Towards Automating ML Research with general-purpose meta-learners @ UCL DARK
55:14
Louis Kirsch - Towards Automating ML Research with general-purpose meta-learners @ UCL DARK
Andrew Lampinen - Comparing Language Models to Humans: Reasoning & Grammer @ UCL DARK
36:29
Andrew Lampinen - Comparing Language Models to Humans: Reasoning & Grammer @ UCL DARK
Nathan Lambert - Reinforcement Learning from Human Feedback @ UCL DARK
47:16
Nathan Lambert - Reinforcement Learning from Human Feedback @ UCL DARK
Micah Carroll - Uni[MASK]: Unified Inference in Sequential Decision Problems @ UCL DARK
39:07
Micah Carroll - Uni[MASK]: Unified Inference in Sequential Decision Problems @ UCL DARK
Sebastian Borgeaud - Efficient Training of Large Language Models @ UCL DARK
34:52
Sebastian Borgeaud - Efficient Training of Large Language Models @ UCL DARK
Matthew Fontaine - Quality Diversity Scenario Generation for Robust Autonomy @ UCL DARK
40:33
Matthew Fontaine - Quality Diversity Scenario Generation for Robust Autonomy @ UCL DARK
Wojciech Czarnecki - On the Geometry of Competitive Games @ UCL DARK
53:57
Wojciech Czarnecki - On the Geometry of Competitive Games @ UCL DARK
Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning - CoLLAs 2022
22:24
Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning - CoLLAs 2022
Kenneth O. Stanley - Novel Opportunities in Open-Endedness @ UCL DARK
52:22
Kenneth O. Stanley - Novel Opportunities in Open-Endedness @ UCL DARK
Franziska Meier - Lifelong Learning for Robotics @ UCL DARK
47:41
Franziska Meier - Lifelong Learning for Robotics @ UCL DARK
Sergey Levine - Understanding the World Through Action @ UCL DARK
59:27
Sergey Levine - Understanding the World Through Action @ UCL DARK
Thomas Kipf - Learning Structured Models of the World @ UCL DARK
45:37
Thomas Kipf - Learning Structured Models of the World @ UCL DARK
Max Jaderberg - Open-Ended Learning Leads to Generally Capable Agents @ UCL DARK
52:28
Max Jaderberg - Open-Ended Learning Leads to Generally Capable Agents @ UCL DARK
Erik Wijmans - Training Virtual Robots in Realistic Simulators @ UCL DARK
47:16
Erik Wijmans - Training Virtual Robots in Realistic Simulators @ UCL DARK
Katja Hofmann - Towards Human-Like And Collaborative AI in Video Games @ UCL DARK
44:55
Katja Hofmann - Towards Human-Like And Collaborative AI in Video Games @ UCL DARK
Matthew Hausknecht - Towards Knowledge Grounded Text Agents @ UCL DARK
43:56
Matthew Hausknecht - Towards Knowledge Grounded Text Agents @ UCL DARK
Sam Gershman - Using Video Games To Reverse Engineer Human Intelligence @ UCL DARK
37:06
Sam Gershman - Using Video Games To Reverse Engineer Human Intelligence @ UCL DARK
Amy Zhang - Exploring Context for Better Generalization in Reinforcement Learning @ UCL DARK
47:46
Amy Zhang - Exploring Context for Better Generalization in Reinforcement Learning @ UCL DARK
Felix Hill - Some Reasons To Do Embodied Machine Learning @ UCL DARK
48:13
Felix Hill - Some Reasons To Do Embodied Machine Learning @ UCL DARK
Jessica Hamrick - Mental Simulation, Imagination, and Model-Based Deep RL @ UCL DARK
38:39
Jessica Hamrick - Mental Simulation, Imagination, and Model-Based Deep RL @ UCL DARK
Jacob Andreas - Grounded Language Learning Without Grounded Supervision @ UCL DARK
52:17
Jacob Andreas - Grounded Language Learning Without Grounded Supervision @ UCL DARK
Yuandong Tian - Finding Good Representation for Search and Exploration in RL @ UCL DARK
47:44
Yuandong Tian - Finding Good Representation for Search and Exploration in RL @ UCL DARK
Simon Lucas - Evolutionary Algorithms and Game AI @ UCL DARK
37:32
Simon Lucas - Evolutionary Algorithms and Game AI @ UCL DARK