Cover Image

Fast Non-Episodic Finite-Horizon RL with K-Step Lookahead Thresholding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xu, Jiamin, Gan, Kyra
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

From Restless to Contextual: A Thresholding Bandit Reformulation For Finite-horizon Improvement
by: Xu, Jiamin, et al.
Published: (2025)

Integrating Causal DAGs in Deep RL: Activating Minimal Markovian States with Multi-Order Exposure
by: Xu, Jiamin, et al.
Published: (2026)

Reinforcement Learning with Multi-Step Lookahead Information Via Adaptive Batching
by: Merlis, Nadav
Published: (2026)

Prior-Aligned Meta-RL: Thompson Sampling with Learned Priors and Guarantees in Finite-Horizon MDPs
by: Zhou, Runlin, et al.
Published: (2025)

LoSAM: Local Search in Additive Noise Models with Mixed Mechanisms and General Noise for Global Causal Discovery
by: Hiremath, Sujai, et al.
Published: (2024)

CSPI-MT: Calibrated Safe Policy Improvement with Multiple Testing for Threshold Policies
by: Cho, Brian M, et al.
Published: (2024)

EARL-BO: Reinforcement Learning for Multi-Step Lookahead, High-Dimensional Bayesian Optimization
by: Cheon, Mujin, et al.
Published: (2024)

Next-Depth Lookahead Tree
by: Lee, Jaeho, et al.
Published: (2025)

Reinforcement Learning with Lookahead Information
by: Merlis, Nadav
Published: (2024)

Generalization and Optimization of SGD with Lookahead
by: Li, Kangcheng, et al.
Published: (2025)

Peeking with PEAK: Sequential, Nonparametric Composite Hypothesis Tests for Means of Multiple Data Streams
by: Cho, Brian, et al.
Published: (2024)

Data Augmentation for Continual RL via Adversarial Gradient Episodic Memory
by: Wu, Sihao, et al.
Published: (2024)

Lookahead Counterfactual Fairness
by: Zuo, Zhiqun, et al.
Published: (2024)

Extending Differential Temporal Difference Methods for Episodic Problems
by: De Asis, Kris, et al.
Published: (2026)

LEAP: Unlocking dLLM Parallelism via Lookahead Early-Convergence Token Detection
by: Zhang, Haohui, et al.
Published: (2026)

Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces
by: Yu, Shixing, et al.
Published: (2026)

The Value of Reward Lookahead in Reinforcement Learning
by: Merlis, Nadav, et al.
Published: (2024)

Bridging RL Theory and Practice with the Effective Horizon
by: Laidlaw, Cassidy, et al.
Published: (2023)

LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generation
by: Ahn, Jinwoo, et al.
Published: (2026)

Federated Causal Inference in Healthcare: Methods, Challenges, and Applications
by: Li, Haoyang, et al.
Published: (2025)

Deep Doubly Debiased Longitudinal Effect Estimation with ICE G-Computation
by: Chen, Wenxin, et al.
Published: (2026)

Smooth Multi-Policy Causal Effect Estimation in Longitudinal Settings
by: Chen, Wenxin, et al.
Published: (2026)

When Additive Noise Meets Unobserved Mediators: Bivariate Denoising Diffusion for Causal Discovery
by: Meier, Dominik, et al.
Published: (2025)

MOSIC: Model-Agnostic Optimal Subgroup Identification with Multi-Constraint for Improved Reliability
by: Chen, Wenxin, et al.
Published: (2025)

Causal Attention with Lookahead Keys
by: Song, Zhuoqing, et al.
Published: (2025)

Policy Mirror Descent with Lookahead
by: Protopapas, Kimon, et al.
Published: (2024)

Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL
by: Wu, Ian, et al.
Published: (2026)

Horizon Reduction Makes RL Scalable
by: Park, Seohong, et al.
Published: (2025)

Lookahead Path Likelihood Optimization for Diffusion LLMs
by: Liu, Xuejie, et al.
Published: (2026)

The Horizon Threshold in Cooperative Multi-Agent Reward-Free Exploration
by: Barnea, Idan, et al.
Published: (2026)

Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation
by: Kitamura, Toshinori, et al.
Published: (2025)

Kernel Debiased Plug-in Estimation: Simultaneous, Automated Debiasing without Influence Functions for Many Target Parameters
by: Cho, Brian, et al.
Published: (2023)

Reward Maximization for Pure Exploration: Minimax Optimal Good Arm Identification for Nonparametric Multi-Armed Bandits
by: Cho, Brian, et al.
Published: (2024)

Dual-Granularity Contrastive Reward via Generated Episodic Guidance for Efficient Embodied RL
by: Liu, Xin, et al.
Published: (2026)

Momentum Boosted Episodic Memory for Improving Learning in Long-Tailed RL Environments
by: Fernandes, Dolton, et al.
Published: (2025)

Scaling Speculative Decoding with Lookahead Reasoning
by: Fu, Yichao, et al.
Published: (2025)

Lookahead identification in adversarial bandits: accuracy and memory bounds
by: Brukhim, Nataly, et al.
Published: (2026)

From Guess2Graph: When and How Can Unreliable Experts Safely Boost Causal Discovery in Finite Samples?
by: Hiremath, Sujai, et al.
Published: (2025)

Lookahead Drifting Model
by: Zhang, Guoqiang, et al.
Published: (2026)

Contextual Bandits with Budgeted Information Reveal
by: Gan, Kyra, et al.
Published: (2023)