A continuous relaxation of a symbolic planner, operating on probabilistic symbol grounding outputs, lets one-shot imitation learning succeed with far fewer meta-training tasks than policy-network baselines.
One-shot imitation from observing humans via domain-adaptive meta-learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Continuous Relaxation of Symbolic Planner for One-Shot Imitation Learning
A continuous relaxation of a symbolic planner, operating on probabilistic symbol grounding outputs, lets one-shot imitation learning succeed with far fewer meta-training tasks than policy-network baselines.