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.
L., Gabillon, V., and Valko, M
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
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.