pith. sign in

arxiv: 2106.11854 · v1 · pith:A35YLVSOnew · submitted 2021-06-22 · 💻 cs.LG

Off-Policy Reinforcement Learning with Delayed Rewards

classification 💻 cs.LG
keywords rewardsdelayedalgorithmsframeworkintroducelearningoff-policyq-function
0
0 comments X
read the original abstract

We study deep reinforcement learning (RL) algorithms with delayed rewards. In many real-world tasks, instant rewards are often not readily accessible or even defined immediately after the agent performs actions. In this work, we first formally define the environment with delayed rewards and discuss the challenges raised due to the non-Markovian nature of such environments. Then, we introduce a general off-policy RL framework with a new Q-function formulation that can handle the delayed rewards with theoretical convergence guarantees. For practical tasks with high dimensional state spaces, we further introduce the HC-decomposition rule of the Q-function in our framework which naturally leads to an approximation scheme that helps boost the training efficiency and stability. We finally conduct extensive experiments to demonstrate the superior performance of our algorithms over the existing work and their variants.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Retroactive Advantage Correction: Closed-Form V-Trace Bias Correction for Delay-Aware RLHF

    cs.LG 2026-06 unverdicted novelty 6.0

    RAC is a closed-form bias correction for delayed rewards in RLHF that is unbiased under full mass reinjection of the delay kernel and reduces to V-trace with no delay.

  2. Delay-Empowered Causal Hierarchical Reinforcement Learning

    cs.LG 2026-05 unverdicted novelty 6.0

    DECHRL models causal structures and stochastic delay distributions within hierarchical RL and incorporates them into a delay-aware empowerment objective to improve performance under temporal uncertainty.

  3. From Bootstrapping to Sequence Modeling: A Unified Generative Framework for Personalized Landing-Page Modeling

    cs.IR 2026-06 unverdicted novelty 5.0

    GLAN replaces CQL bootstrapping with Decision Transformer sequence modeling for PLPM, using global inter-day (L-RTG) and local session (HRM) modules to achieve +0.158% DAU and +0.108% LT gains in Kuaishou online tests.