Week 10: RL and Language
Core Readings Tuesday:
Shunyu Yao, Rohan Rao, Matthew Hausknecht, Karthik Narasimhan (2020). Keep CALM and Explore: Language Models for Action Generation in Text-based Games
S.R.K. Branavan, David Silver, Regina Barzilay (2014). Learning to Win by Reading Manuals in a Monte-Carlo Framework
Core Readings Thursday:
Yoav Artzi, Luke Zettlemoyer (2013). Weakly Supervised Learning of Semantic Parsers for Mapping Instructions to Actions
Jacob Andreas, Dan Klein, Sergey Levine (2017). Learning with Latent Language.
Additional Readings Tuesday:
- Part 1:
Karthik Narasimhan, Tejas Kulkarni, Regina Barzilay (2015). Language Understanding for Text-based Games Using Deep Reinforcement Learning
Prithviraj Ammanabrolu, Matthew Hausknecht (2020). Graph Constrained Reinforcement Learning for Natural Language Action Spaces
Xiaoxiao Guo, Mo Yu, Yupeng Gao, Chuang Gan, Murray Campbell, Shiyu Chang (2020). Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning
Mohit Shridhar, Xingdi Yuan, Marc-Alexandre Côté, Yonatan Bisk, Adam Trischler, Matthew Hausknecht (2020). ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
Karthik Narasimhan, Adam Yala, Regina Barzilay (2016). Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning
- Part 2:
Karthik Narasimhan, Regina Barzilay, Tommi Jaakkola (2017). Grounding Language for Transfer in Deep Reinforcement Learning
Victor Zhong, Tim Rocktäschel, Edward Grefenstette (2019). RTFM: Generalising to Novel Environment Dynamics via Reading
Austin W. Hanjie, Victor Zhong, Karthik Narasimhan (2021). Grounding Language to Entities and Dynamics for Generalization in Reinforcement Learning
Additional Readings Thursday:
- language -> actions
S.R.K. Branavan, Harr Chen, Luke Zettlemoyer, Regina Barzilay (2009). Reinforcement Learning for Mapping Instructions to Actions
Hongyuan Mei, Mohit Bansal, Matthew R. Walter (2015). Listen, Attend, and Walk: Neural Mapping of Navigational Instructions to Action Sequences
- language -> constraints, costs & goals
Stefanie Tellex, Thomas Kollar, Steven Dickerson, Matthew R. Walter, Ashis Gopal Banerjee, Seth Teller, Nicholas Roy (2011). Understanding Natural Language Commands for Robotic Navigation and Mobile Manipulation
- NL supervision
Jacob Andreas, Dan Klein, Sergey Levine (2016). Modular Multitask Reinforcement Learning with Policy Sketches
Pratyusha Sharma, Antonio Torralba, Jacob Andreas (2021). Skill Induction and Planning with Latent Language