markov-decision-process

Tag

Cards List
#markov-decision-process

Bayesian $\kappa$-Explorer for Minimax Model Estimation in MDPs

arXiv cs.LG ↗ · yesterday Cached

The paper introduces Bayesian κ-Explorer, which places Dirichlet priors on MDP transition distributions to simplify minimax transition estimation by replacing confidence-set optimization with a closed-form posterior variance exploration signal, while retaining the Õ(T^-1/3) convergence rate of the frequentist κ-Explorer and showing lower worst-case estimation errors on Pendulum, Mountain Car, and Taxi.

0 favorites 0 likes
#markov-decision-process

$M^3$: A Multi-LLM System for Multi-Turn Jailbreaking as a Markov Decision Process

arXiv cs.AI ↗ · 2026-10-26

论文提出 M³,一个将多轮越狱形式化为有限时域马尔可夫决策过程(MDP)的自动化红队框架,在两个基准、六个目标模型上将攻击成功率(ASR@5)提升最高达 53%,显著优于现有黑盒多轮红队方法。

0 favorites 0 likes
#markov-decision-process

Windowed A-K-MDP

arXiv cs.AI ↗ · 2026-09-15 Cached

Windowed A-K-MDP algorithm improves MDP state abstraction for conservation by generating feasible partitions within a window, reducing decision loss in 25 out of 33 test cases compared to binary search methods.

0 favorites 0 likes
#markov-decision-process

Progressive Point Matching (8 minute read)

TLDR AI ↗ · 2026-09-09 Cached

Progressive Point Matching (PPM) is a framework proposed to assign partial credit in reinforcement learning for long-horizon tasks in LLMs, addressing the inefficiency of sparse outcome rewards by treating reasoning as paths through a Markovian state space.

0 favorites 0 likes
#markov-decision-process

Discrete-Time MDP Modeling for Multi-Item Capacitated Lot Sizing with Stochastic Demand Timing

arXiv cs.AI ↗ · 2026-09-02 Cached

This paper formulates a multi-item capacitated lot-sizing problem with stochastic demand timing as a discrete-time MDP and proposes a genetic algorithm to solve it, demonstrating efficiency on benchmark instances.

0 favorites 0 likes
#markov-decision-process

Individual Disempowerment through an Advice Channel: Control Loss when Influence is Endogenous

arXiv cs.AI ↗ · 2026-08-18 Cached

This paper models human-AI interactions where an AI only gives advice, showing how reliance can increase and lead to disempowerment, and analyzes the effectiveness of safety constraints like influence bounds.

0 favorites 0 likes
#markov-decision-process

Fashion Outfit Generation via Unified Sequential Composition Models

arXiv cs.LG ↗ · 2026-08-17 Cached

This paper proposes a Unified Sequential Composition Model (USCM) and Latent Expansion Monte Carlo Tree Search (LE-MCTS) for fashion outfit generation, achieving state-of-the-art performance on multiple datasets.

0 favorites 0 likes
#markov-decision-process

Posture and Sustainment Optimization Under Adversarial Uncertainty

arXiv cs.AI ↗ · 2026-08-07 Cached

This paper introduces a scenario-weighted adversarially robust posture optimization engine for military asset allocation, proposing CEV and RobustCEV optimizers that outperform greedy baselines under adversarial threat uncertainty.

0 favorites 0 likes
#markov-decision-process

From Passive Generation to Investigation: A Proactive Scientific Peer Review Agent

arXiv cs.CL ↗ · 2026-06-12 Cached

This paper proposes ProReviewer, an LLM-based scientific peer review agent formulated as a Markov Decision Process, which proactively investigates papers by maintaining a structured review log and outperforms existing methods across multiple quality dimensions.

0 favorites 0 likes
#markov-decision-process

Reinforcement Learning with Pairwise Preferences in Long-Term Decision Problems

arXiv cs.LG ↗ · 2026-06-02 Cached

This paper introduces the Markov decision contest, a new problem model for reinforcement learning with pairwise preferences. It proves optimality guarantees for stationary policies, exact solvability in P, and presents a learning-efficient approximate algorithm.

0 favorites 0 likes
#markov-decision-process

Small RL Controller, Large Language Model: RL-Guided Adaptive Sampling for Test-Time Scaling

Hugging Face Daily Papers ↗ · 2026-06-02 Cached

This paper formulates adaptive sampling for large language models as a Markov decision process and trains a lightweight RL controller to balance correctness, latency, and computational cost, achieving improved trade-offs.

0 favorites 0 likes
#markov-decision-process

Iterative Critique-and-Routing Controller for Multi-Agent Systems with Heterogeneous LLMs

arXiv cs.AI ↗ · 2026-05-12 Cached

This paper introduces a critique-and-routing controller for multi-agent LLM systems that formulates coordination as a sequential decision problem. It uses policy gradients to optimize the controller for iterative refinement, outperforming baselines while reducing reliance on top-tier models.

0 favorites 0 likes
#markov-decision-process

What are MDPs? And how can we Solve them?

ML at Berkeley ↗ · 2021-02-23 Cached

This article explains the fundamentals of Markov Decision Processes (MDPs), a core framework in deep reinforcement learning, using an educational example of a student's daily decisions.

0 favorites 0 likes
← Back to home

Submit Feedback