Establishes maximal concentration bounds for stochastic approximation under heavy-tailed Markovian noise, with tails ranging from sub-Gaussian to heavier than Weibull depending on step sizes and contractivity properties, plus a truncation argument for unbounded noise.
hub
Machine learning , volume=
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Consumers transfer brand-level regularities across contexts using low-D boundedly rational meta-learning approximations that fit choice data better than no-transfer or fully integrated Bayesian benchmarks.
A diameter criterion tied to a potential function certifies convergence of difference inclusions, enabling discrete proofs for first-order optimization methods with diminishing steps.
ATD(λ) adapts TD(λ) in MARL via a density ratio estimator on past/current replay buffers to assign λ per state-action pair, yielding competitive or better results than fixed-λ QMIX and MAPPO on SMAC and Gfootball.
Temporal correlations from lazy random walks enable efficient SGD learning of k-juntas via temporal-difference loss on ReLU networks, achieving linear sample complexity in d.
CaTR applies value-decomposed RL with hierarchical conflict-aware observations to achieve better safety-efficiency trade-offs than planning, optimization, and standard RL baselines in a realistic airport taxiway simulation.
Listwise Policy Optimization explicitly performs target-projection on the LLM response simplex, unifying and improving group-based RLVR methods with monotonic improvement and flexible divergences.
New Berry-Esseen bounds for multivariate martingale difference sequences achieve n^{-1/4} rate and polylog(d) dimension dependence in Kolmogorov distance.
QHyer replaces return-to-go with a state-conditioned Q-estimator and adds a gated hybrid attention-mamba backbone to achieve state-of-the-art performance in offline goal-conditioned RL on both Markovian and non-Markovian datasets.
PRIME enables online process reward model updates in LLM RL using implicit rewards from rollouts and outcome labels, yielding 15.1% average gains on reasoning benchmarks and surpassing a stronger instruct model with 10% of the data.
citing papers explorer
-
Value-Decomposed Reinforcement Learning Framework for Taxiway Routing with Hierarchical Conflict-Aware Observations
CaTR applies value-decomposed RL with hierarchical conflict-aware observations to achieve better safety-efficiency trade-offs than planning, optimization, and standard RL baselines in a realistic airport taxiway simulation.