AI & ML
Efficient Variance-Aware Reinforcement Learning in Time-Inhomogeneous Linear MDPs
arXiv stat.ML0 views
arXiv:2611.23596v1 Announce Type: cross Abstract: We study variance-dependent reinforcement learning in episodic time-inhomogeneous linear Markov decision processes (MDPs) with feature dimension $d$, horizon $H$, and $K$ episodes. While recent works have established variance-dependent regret with $\tilde{O}(1)$ deterministic-regime overhead for linear mixture MDPs (Zhao et al., 2023) and worst-case nearly minimax optimal regret $\tilde{O}(d\sqrt{H^3 K} + d^7 H^8)$ for linear MDPs (He et al., 2023),, existing variance-aware analyses for linear MDPs (Li and Sun, 2023; Huang et al., 2023) rely on a coarse concentration step whose resulting regret guarantees retain a polynomial $\tilde{O}(K^{1/4})$ additive term even in deterministic environments. We propose VA-LSVI-UCB++, a computationally efficient algorithm that achieves the variance-dependent regret bound $\tilde{O}(d\sqrt{H\min\{\mathrm{Var}_K^*,\mathrm{Var}_K^\pi\}}+d^5H^4)$, where $\mathrm{Var}_K^*$ and $\mathrm{Var}_K^\pi$ denote the cumulative conditional variances of the optimal value function and the played policies' value functions along the realized trajectory. Our result adapts to the minimum of the two realized trajectory variances, recovers the worst-case minimax optimal leading term $\tilde{O}(d\sqrt{H^3 K})$, and collapses to $\tilde{O}(d^5 H^4)$ in deterministic environments, free of polynomial-in-$K$ dependency. At the core of our analysis is a simultaneous three-way reference-advantage decomposition for the optimistic, pessimistic, and squared value function estimators coupled with variance self-bounding and Freedman-type value-difference arguments, which tightens the pessimistic and second-moment confidence radii by a factor of $\tilde{O}(d H)$ and removes the inverse-variance-floor blowup.
Source:https://arxiv.org/abs/2611.23596PreviousStability of Parallel Transport Convolution under Riemannian Metric PerturbationsNextVariable Length Diffuse Everything: Arbitrary Length Generative Modeling on Arbitrary State Spaces
Related posts
A Matching Lower Bound for Online Smooth Calibration
0arXiv stat.ML
How Path Integral Diffusion Decides a Finite Spin Glass
0arXiv stat.ML
Prescriptive Learning of Linear Policies with Feasibility Guarantees for Binary Decision-Making
0arXiv stat.ML
IQS-BO: In-Context Query Selection for Bayesian Optimisation
0arXiv stat.ML
Swiss-Knife: A Framework for Reconfigurable Externalised Multi-Objective Alignment at Decode Time
0arXiv stat.ML
Inverse Design for Conditional Distribution Matching
0arXiv stat.ML