A modified harmonic mean operator correctly computes reward rates in non-stationary SMDPs for average-reward reinforcement learning.
Das, Abhijit Gosavi, Sridhar Mahadevan, and Nicholas Marchalleck
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
-
A Harmonic Mean Formulation of Average Reward Reinforcement Learning in SMDPs
A modified harmonic mean operator correctly computes reward rates in non-stationary SMDPs for average-reward reinforcement learning.