The paper introduces a modified geometric mean regularizer for multi-step Q-learning and claims it captures time-average growth, but the key theoretical and empirical supports are weak.
Reinforcement learning with non-ergodic reward in- crements: robustness via ergodicity transformations,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Beyond expected value: geometric mean optimization for long-term policy performance in reinforcement learning
The paper introduces a modified geometric mean regularizer for multi-step Q-learning and claims it captures time-average growth, but the key theoretical and empirical supports are weak.