all AI news
Understanding Game-Playing Agents with Natural Language Annotations. (arXiv:2204.07531v1 [cs.CL])
April 18, 2022, 1:11 a.m. | Nicholas Tomlin, Andre He, Dan Klein
cs.CL updates on arXiv.org arxiv.org
We present a new dataset containing 10K human-annotated games of Go and show
how these natural language annotations can be used as a tool for model
interpretability. Given a board state and its associated comment, our approach
uses linear probing to predict mentions of domain-specific terms (e.g., ko,
atari) from the intermediate state representations of game-playing agents like
AlphaGo Zero. We find these game concepts are nontrivially encoded in two
distinct policy networks, one trained via imitation learning and another …
agents annotations arxiv game language natural natural language playing
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
Senior Marketing Data Analyst
@ Amazon.com | Amsterdam, North Holland, NLD
Senior Data Analyst
@ MoneyLion | Kuala Lumpur, Kuala Lumpur, Malaysia
Data Management Specialist - Office of the CDO - Chase- Associate
@ JPMorgan Chase & Co. | LONDON, LONDON, United Kingdom
BI Data Analyst
@ Nedbank | Johannesburg, ZA
Head of Data Science and Artificial Intelligence (m/f/d)
@ Project A Ventures | Munich, Germany
Senior Data Scientist - GenAI
@ Roche | Hyderabad RSS