The authors extend behavioral entropy to continuous spaces, derive k-nearest-neighbor estimators and a reward function, and show that datasets generated by this objective improve downstream offline RL performance over standard entropy-based baselines.
For a given set S ⊂ X, radius r, and m > 0, let N (S, r) denote the covering number, the minimum number of balls of radius r needed to cover S
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Behavioral Entropy-Guided Dataset Generation for Offline Reinforcement Learning
The authors extend behavioral entropy to continuous spaces, derive k-nearest-neighbor estimators and a reward function, and show that datasets generated by this objective improve downstream offline RL performance over standard entropy-based baselines.