SmoothCruiser achieves O~(1/epsilon^4) problem-independent sample complexity for value estimation in entropy-regularized MDPs and games via a generative model.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Platypoos is a scale-free adaptive planning algorithm with sample complexity bounds that hold simultaneously across discount factors and reward scales, accompanied by a matching lower bound.
citing papers explorer
-
Planning in entropy-regularized Markov decision processes and games
SmoothCruiser achieves O~(1/epsilon^4) problem-independent sample complexity for value estimation in entropy-regularized MDPs and games via a generative model.
-
Scale-free adaptive planning for deterministic dynamics & discounted rewards
Platypoos is a scale-free adaptive planning algorithm with sample complexity bounds that hold simultaneously across discount factors and reward scales, accompanied by a matching lower bound.