Context-sensitive abstractions learned during training allow TD(λ) to reach higher sample efficiency than baselines across continuous-state parameterized-action domains.
4d): This domain models a complex, multi-city delivery problem
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Context-Sensitive Abstractions for Reinforcement Learning with Parameterized Actions
Context-sensitive abstractions learned during training allow TD(λ) to reach higher sample efficiency than baselines across continuous-state parameterized-action domains.