Harmonized benchmarking of expert-guided RL methods on continuous control tasks surfaces three failure modes and produces a testable decision rule for method selection keyed on expert quality, task termination, and perturbation type.
IEEE International Conference on Robotics and Automation (ICRA) , year =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
When (and How) to Trust the Expert: Diagnosing Query-Time Expert-Guided Reinforcement Learning
Harmonized benchmarking of expert-guided RL methods on continuous control tasks surfaces three failure modes and produces a testable decision rule for method selection keyed on expert quality, task termination, and perturbation type.