TIDBD, which adapts one learning rate per feature, performed comparably to hand-tuned temporal-difference learning on a real robotic arm and produced distinct step-size signatures for simulated stuck and broken sensors.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Examining the Use of Temporal-Difference Incremental Delta-Bar-Delta for Real-World Predictive Knowledge Architectures
TIDBD, which adapts one learning rate per feature, performed comparably to hand-tuned temporal-difference learning on a real robotic arm and produced distinct step-size signatures for simulated stuck and broken sensors.