ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2209.01876
10
0

SlateFree: a Model-Free Decomposition for Reinforcement Learning with Slate Actions

5 September 2022
A. Giovanidis
ArXivPDFHTML
Abstract

We consider the problem of sequential recommendations, where at each step an agent proposes some slate of NNN distinct items to a user from a much larger catalog of size K>>NK>>NK>>N. The user has unknown preferences towards the recommendations and the agent takes sequential actions that optimise (in our case minimise) some user-related cost, with the help of Reinforcement Learning. The possible item combinations for a slate is (KN)\binom{K}{N}(NK​), an enormous number rendering value iteration methods intractable. We prove that the slate-MDP can actually be decomposed using just KKK item-related QQQ functions per state, which describe the problem in a more compact and efficient way. Based on this, we propose a novel model-free SARSA and Q-learning algorithm that performs NNN parallel iterations per step, without any prior user knowledge. We call this method \texttt{SlateFree}, i.e. free-of-slates, and we show numerically that it converges very fast to the exact optimum for arbitrary user profiles, and that it outperforms alternatives from the literature.

View on arXiv
Comments on this paper