Year: 2017
Type: preprint
Abstract: We build deep RL agents that execute declarative programs expressed in formal language. The agents learn to ground the terms in this language in their environment, and can generalize their behavior at test time to execute new programs that refer to objects that were not referenced during training. The agents develop disentangled interpretable representations that allow them to generalize to a wide variety of zero-shot semantic tasks.
Source: arXiv (Cornell University)
Authors: Denil, Misha, Colmenarejo, Sergio Gómez, Cabi, Serkan, Saxton, David, de Freitas, Nando
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3038064289