LGOCMLOct 2, 2025

Reinforcement Learning with Action-Triggered Observations

arXiv:2510.02149v1h-index: 2
Originality Highly original
AI Analysis

This addresses a constraint common in real-world applications like robotics or sensor networks, providing a theoretical foundation for efficient learning with sporadic observations.

The paper tackles reinforcement learning with state observations triggered stochastically by actions, formulating it as ATST-MDPs and proposing the action-sequence learning paradigm. It introduces ST-LSVI-UCB, achieving a regret bound of ̃O(√Kd^3(1-γ)^{-3}) under linear MDP assumptions.

We study reinforcement learning problems where state observations are stochastically triggered by actions, a constraint common in many real-world applications. This framework is formulated as Action-Triggered Sporadically Traceable Markov Decision Processes (ATST-MDPs), where each action has a specified probability of triggering a state observation. We derive tailored Bellman optimality equations for this framework and introduce the action-sequence learning paradigm in which agents commit to executing a sequence of actions until the next observation arrives. Under the linear MDP assumption, value-functions are shown to admit linear representations in an induced action-sequence feature map. Leveraging this structure, we propose off-policy estimators with statistical error guarantees for such feature maps and introduce ST-LSVI-UCB, a variant of LSVI-UCB adapted for action-triggered settings. ST-LSVI-UCB achieves regret $\widetilde O(\sqrt{Kd^3(1-γ)^{-3}})$, where $K$ is the number of episodes, $d$ the feature dimension, and $γ$ the discount factor (per-step episode non-termination probability). Crucially, this work establishes the theoretical foundation for learning with sporadic, action-triggered observations while demonstrating that efficient learning remains feasible under such observation constraints.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes