pith. sign in

Corruption-robust exploration in episodic reinforcement learning

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2025 1

verdicts

UNVERDICTED 1

representative citing papers

Corruption-Tolerant Asynchronous Q-Learning with Near-Optimal Rates

cs.LG · 2025-09-10 · unverdicted · novelty 6.0

A novel robust asynchronous Q-learning algorithm achieves finite-time convergence rates that match clean-data bounds up to an additive term proportional to the corruption fraction, with a matching information-theoretic lower bound.

citing papers explorer

Showing 1 of 1 citing paper.

  • Corruption-Tolerant Asynchronous Q-Learning with Near-Optimal Rates cs.LG · 2025-09-10 · unverdicted · none · ref 40

    A novel robust asynchronous Q-learning algorithm achieves finite-time convergence rates that match clean-data bounds up to an additive term proportional to the corruption fraction, with a matching information-theoretic lower bound.