This talk is part of the NLP Seminar Series.

Knowledge Intensive Reinforcement Learning

Tim Rocktäschel, Facebook AI Research/UCL
Date: 10:00am - 11:00am PT, Apr 22 2021
Venue: Zoom (link hidden)


Progress in Reinforcement Learning (RL) methods goes hand-in-hand with the development of challenging environments that test the limits of current approaches. While existing RL environments are either sufficiently complex or based on fast simulation, they are rarely both these things. Moreover, research in RL has predominantly focused on environments that can be approached tabula rasa, i.e., without agents requiring transfer of any domain or world knowledge outside of the simulated environment. I will talk about the NetHack Learning Environment (NLE), a scalable, procedurally generated, stochastic, rich, and challenging environment for research based on the popular single-player terminal-based rogue like game, NetHack. We argue that NetHack is sufficiently complex to drive long-term research on problems such as exploration, planning, skill acquisition, and language-conditioned RL, while dramatically reducing the computational resources required to gather a large amount of experience. Interestingly, this game is extremely challenging even for human players who often need many years to solve it the first time and who generally consult external natural language knowledge sources like the NetHack Wiki to improve their skills. Towards the end of the talk, I will also cover our recent work on conditioning on large-scale textual knowledge sources and how these techniques might pave the way for sample efficient RL in complex, more real-world environments in the future.


Tim is a Research Scientist at Facebook AI Research (FAIR) London, a Lecturer at the Centre for Artificial Intelligence in the Department of Computer Science at University College London (UCL), and a Scholar of the European Laboratory for Learning and Intelligent Systems (ELLIS). Prior to that, he was a Postdoctoral Researcher in Reinforcement Learning at the University of Oxford, a Junior Research Fellow in Computer Science at Jesus College, and a Stipendiary Lecturer in Computer Science at Hertford College. Tim obtained his Ph.D. from UCL under the supervision of Sebastian Riedel, and he was awarded a Microsoft Research Ph.D. Scholarship in 2013 and a Google Ph.D. Fellowship in 2017. His work focuses on reinforcement learning in open-ended environments that require intrinsically motivated agents capable of transferring commonsense, world and domain knowledge in order to systematically generalize to novel situations.