Adaptive exploration for multi-reward multi-policy evaluation, with an instance-dependent lower bound and a convex relaxation algorithm.
This choice encourages to select under-sampled actions for β >0, while for β = 0 we obtain a uniform forcing policy πf,t(a|s) = 1/A
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Adaptive Exploration for Multi-Reward Multi-Policy Evaluation
Adaptive exploration for multi-reward multi-policy evaluation, with an instance-dependent lower bound and a convex relaxation algorithm.