| 2 |
Grounded Language Learning Fast and Slow ...
|
|
|
|
Abstract:
Recent work has shown that large text-based neural language models, trained with conventional supervised learning objectives, acquire a surprising propensity for few- and one-shot learning. Here, we show that an embodied agent situated in a simulated 3D world, and endowed with a novel dual-coding external memory, can exhibit similar one-shot word learning when trained with conventional reinforcement learning algorithms. After a single introduction to a novel object via continuous visual perception and a language prompt ("This is a dax"), the agent can re-identify the object and manipulate it as instructed ("Put the dax on the bed"). In doing so, it seamlessly integrates short-term, within-episode knowledge of the appropriate referent for the word "dax" with long-term lexical and motor knowledge acquired across episodes (i.e. "bed" and "putting"). We find that, under certain training conditions and with a particular memory writing mechanism, the agent's one-shot word-object binding generalizes to novel ...
|
|
Keyword:
Artificial Intelligence cs.AI; Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.2009.01719
https://arxiv.org/abs/2009.01719
|
|
BASE
|
|
Hide details
|
|
|
| 3 |
Shaping representations through communication: community size effect in artificial learning systems ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|
|
