Hitting-Time Bounds for Asynchronous Q-Learning
arXiv:2610.13901v1 Announce Type: new Abstract: We study the last iterate of standard asynchronous Q-learning from a single trajectory of a finite Markov decision process. The trajectory follows a fixed behavior policy whose state--action chain is irreducible and may be periodic. For discount facto…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-10-12 04:00 · arXiv stat.ML
Hitting-Time Bounds for Asynchronous Q-Learning