Policy gradient formulas are derived for random, policy-dependent time horizons, and the corrected state-space factor (expected runtime) materially improves convergence in experiments.
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
ACCEPT 1representative citing papers
citing papers explorer
-
Reinforcement Learning with Random Time Horizons
Policy gradient formulas are derived for random, policy-dependent time horizons, and the corrected state-space factor (expected runtime) materially improves convergence in experiments.