Tag
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.
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。
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.