A Guide agent trained with a two-token discrete bottleneck learns an emergent guidance language that speeds up a new agent's navigation learning in BabyAI and can be partially reverse-engineered into action commands.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Mastering emergent language: learning to guide in simulated navigation
A Guide agent trained with a two-token discrete bottleneck learns an emergent guidance language that speeds up a new agent's navigation learning in BabyAI and can be partially reverse-engineered into action commands.