On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “S-rectangular”

Near-Optimal Sample Complexities of Divergence-based S-rectangular Distributionally Robust Reinforcement Learningcs.LG

Paper studies S-rectangular DR-RL models for robust reinforcement learning with near-optimal sample complexity.

problem Addressing distributional discrepancies in reinforcement learning environments.

method Empirical value iteration algorithm for divergence-based S-rectangular DR-RL models.

result Near-optimal sample complexity bound of

O(|\mathcal{S}||\mathcal{A}|(1-γ)^{-4}\varepsilon^{-2})

reinforcement learning distributionally robust S-rectangular DR-RL sample complexity

2025-05-18abs ↗pdf ↗

Towards Theoretical Understandings of Robust Markov Decision Processes: Sample Complexity and Asymptoticsstat.ML

Paper studies robust MDPs, improving sample complexity and asymptotic performance.

problem Optimal robust policy and value function in robust MDPs with generative models.

method Improves prior results on non-asymptotic and asymptotic performances of robust MDPs, considering various uncertainty sets.

result Improved sample complexity and asymptotic normality of optimal robust value function.

robust MDPs sample complexity asymptotic performance uncertainty sets optimal policy

2021-05-09abs ↗pdf ↗

Towards Minimax Optimality of Model-based Robust Reinforcement Learningcs.LG

Paper improves sample complexity for robust reinforcement learning.

problem Minimizing sample complexity for robust reinforcement learning.

method Analyzes sample complexity for any planning algorithm in robust MDPs.

result Improves sample complexity to O(H^4 |S| |A| / ε^2) for robust MDPs.

Reinforcement Learning Robustness Markov Decision Processes Sample Complexity Optimality

2023-02-10abs ↗pdf ↗

On the Foundation of Distributionally Robust Reinforcement Learningcs.LG

New framework for robust reinforcement learning policies in uncertain environments.

problem Robust reinforcement learning policies in environments with distributional shifts.

method Comprehensive modeling framework centered around robust Markov decision processes (RMDPs).

result Existence and conditions for the dynamic programming principle (DPP) in RMDPs.

distributionally robust reinforcement learning robust Markov decision processes dynamic programming principle reinforcement learning algorithms environment shifts

2023-11-15abs ↗pdf ↗