Pruning decision-tree versions of RL policies with reward-guarded operators reduces rule counts while retaining most task reward.
Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics , pages =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Interpretable reinforcement learning with decision-tree pruning
Pruning decision-tree versions of RL policies with reward-guarded operators reduces rule counts while retaining most task reward.