The NetHack Learning Environment
Hard and diverse tasks in complex environments drive progress in Reinforcement Learning (RL) research. In this talk, I will present the NetHack Learning Environment: a scalable, procedurally generated, rich and challenging environment for RL research based on the popular single-player terminal-based roguelike NetHack game, along with a suite of initial tasks. This environment is sufficiently complex to drive long-term research on exploration, planning, skill acquisition and complex policy learning, while dramatically reducing the computational resources required to gather a large amount of experience. I compare this environment and task suite to existing alternatives, and discuss why it is an ideal medium for testing the robustness and systematic generalization of RL agents. Lastly, I demonstrate empirical success for early stages of the game using a distributed deep RL baseline, and present a comprehensive qualitative analysis of agents trained in the environment.
Tim Rocktäschel is a Research Scientist at Facebook AI Research (FAIR) London and a Lecturer in the Department of Computer Science at University College London (UCL). At UCL, he is a member of the UCL Centre for Artificial Intelligence and the UCL Natural Language Processing group. Prior to that, he was a Postdoctoral Researcher in the Whiteson Research Lab, a Stipendiary Lecturer in Computer Science at Hertford College, and a Junior Research Fellow in Computer Science at Jesus College, at the University of Oxford.
Tim obtained his Ph.D. in the Machine Reading group at University College London under the supervision of Sebastian Riedel. He received a Google Ph.D. Fellowship in Natural Language Processing in 2017 and a Microsoft Research Ph.D. Scholarship in 2013. In Summer 2015, he worked as a Research Intern at Google DeepMind. In 2012, he obtained his Diploma (equivalent to M.Sc) in Computer Science from the Humboldt-Universität zu Berlin. Between 2010 and 2012, he worked as Student Assistant and in 2013 as Research Assistant in the Knowledge Management in Bioinformatics group at Humboldt-Universität zu Berlin.
Tim's research focuses on sample-efficient and interpretable machine learning models that learn from world, domain, and commonsense knowledge in symbolic and textual form. His work is at the intersection of deep learning, reinforcement learning, natural language processing, program synthesis, and formal logic.