An empirical study proposes hyperparameter settings that improve rating-based RL on three control tasks, but the gains are measured on the same runs used to select the settings.
Title resolution pending
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
-
Performance Optimization of Ratings-Based Reinforcement Learning
An empirical study proposes hyperparameter settings that improve rating-based RL on three control tasks, but the gains are measured on the same runs used to select the settings.