Define now the policy π(u|s) = P (u|s, π(s))

The reward function instead is ¯r(s) = r(s, π(s))

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

browse 1 citing papers

representative citing papers

cs.LG · 2025-02-04 · conditional · novelty 6.0

Adaptive exploration for multi-reward multi-policy evaluation, with an instance-dependent lower bound and a convex relaxation algorithm.

Showing 1 of 1 citing paper.

Adaptive Exploration for Multi-Reward Multi-Policy Evaluation cs.LG · 2025-02-04 · conditional · none · ref 1
Adaptive exploration for multi-reward multi-policy evaluation, with an instance-dependent lower bound and a convex relaxation algorithm.