Establishes last-iterate convergence rates for on-policy Q-learning under minimal irreducibility assumptions, with sample complexity O(1/ξ²) matching off-policy up to exploration factors.
Reinforcementlearningbasedrecommendersystems: A survey.ACM Comput
5 Pith papers cite this work, alongside 470 external citations. Polarity classification is still indexing.
5
Pith papers citing it
470
external citations · OpenAlex
representative citing papers
A lightweight VLM inspecting SMAC policy videos produces open-ended multi-agent curricula that outperform text-only ablations and PLR scalar-score methods on held-out maps.
Vanishing L2 regularization yields provable convergence for softmax MAB policies and improves empirical performance.
fcTS corrects and reweights historical observations via drift models for linear, periodic, and regime-switching non-stationarities in contextual bandits, outperforming forgetting baselines in structured cases.
Introduces semantic Pareto-DQN for multi-objective recommendation that sustains trajectory variance to improve diversity and fairness on MovieLens with limited engagement loss.
citing papers explorer
-
A Minimal-Assumption Analysis of Q-Learning with Time-Varying Policies
Establishes last-iterate convergence rates for on-policy Q-learning under minimal irreducibility assumptions, with sample complexity O(1/ξ²) matching off-policy up to exploration factors.
-
Open-ended Multi-agent Autocurricula via Visual Inspection of Policies with Multi-modal LLMs
A lightweight VLM inspecting SMAC policy videos produces open-ended multi-agent curricula that outperform text-only ablations and PLR scalar-score methods on held-out maps.
-
Vanishing L2 regularization for the softmax Multi Armed Bandit
Vanishing L2 regularization yields provable convergence for softmax MAB policies and improves empirical performance.
-
Flow-Corrected Thompson Sampling for Non-Stationary Contextual Bandits
fcTS corrects and reweights historical observations via drift models for linear, periodic, and regime-switching non-stationarities in contextual bandits, outperforming forgetting baselines in structured cases.
-
Breaking the Filter Bubble: A Semantic Pareto-DQN Framework for Multi-Objective Recommendation
Introduces semantic Pareto-DQN for multi-objective recommendation that sustains trajectory variance to improve diversity and fairness on MovieLens with limited engagement loss.