3 citations · 3 across the 4 of their papers we have counts for
4 papers
Noticing the Watcher: LLM Agents Can Infer CoT Monitoring from Blocking Feedback
Thomas Jiralerspong, Flemming Kondrup, Yoshua Bengio
Chain-of-thought (CoT) monitoring is proposed as a method for overseeing the internal reasoning of language-model agents. Prior work has shown that when models are explicitly infor…
Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learning
Lynn Cherif, Flemming Kondrup, David Venuto +3
Agents that can autonomously navigate the web through a graphical user interface (GUI) using a unified action space (e.g., mouse and keyboard actions) can require very large amount…
Forecaster: Towards Temporally Abstract Tree-Search Planning from Pixels
Thomas Jiralerspong, Flemming Kondrup, Doina Precup +1
The ability to plan at many different levels of abstraction enables agents to envision the long-term repercussions of their decisions and thus enables sample-efficient learning. Th…
Towards Safe Mechanical Ventilation Treatment Using Deep Offline Reinforcement Learning
Flemming Kondrup, Thomas Jiralerspong, Elaine Lau +5
Mechanical ventilation is a key form of life support for patients with pulmonary impairment. Healthcare workers are required to continuously adjust ventilator settings for each pat…