Cover Image

RL2ML: Finite-Rollout Surrogate Objectives from Reinforcement Learning to Maximum Likelihood

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Zheng, Yifu
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

QuRL: Efficient Reinforcement Learning with Quantized Rollout
by: Li, Yuhang, et al.
Published: (2026)

Maximum Likelihood Reinforcement Learning
by: Tajwar, Fahim, et al.
Published: (2026)

EchoRL: Reinforcement Learning via Rollout Echoing
by: Bi, Jinhe, et al.
Published: (2026)

SPEC-RL: Accelerating On-Policy Reinforcement Learning with Speculative Rollouts
by: Liu, Bingshuai, et al.
Published: (2025)

BiCQL-ML: A Bi-Level Conservative Q-Learning Framework for Maximum Likelihood Inverse Reinforcement Learning
by: Park, Junsung
Published: (2025)

MODULI: Unlocking Preference Generalization via Diffusion Models for Offline Multi-Objective Reinforcement Learning
by: Yuan, Yifu, et al.
Published: (2024)

On Rollouts in Model-Based Reinforcement Learning
by: Frauenknecht, Bernd, et al.
Published: (2025)

Instance-Dependent Continuous-Time Reinforcement Learning via Maximum Likelihood Estimation
by: Zhao, Runze, et al.
Published: (2025)

Maximum Entropy Exploration Without the Rollouts
by: Adamczyk, Jacob, et al.
Published: (2026)

OASI: Objective-Aware Surrogate Initialization for Multi-Objective Bayesian Optimization in TinyML Keyword Spotting
by: Garai, Soumen, et al.
Published: (2025)

Jet-RL: Enabling On-Policy FP8 Reinforcement Learning with Unified Training and Rollout Precision Flow
by: Xi, Haocheng, et al.
Published: (2026)

Sparse-RL: Breaking the Memory Wall in LLM Reinforcement Learning via Stable Sparse Rollouts
by: Luo, Sijia, et al.
Published: (2026)

Model-Agnostic Knowledge Guided Correction for Improved Neural Surrogate Rollout
by: Srikishan, Bharat, et al.
Published: (2025)

Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning
by: Xu, Yixuan Even, et al.
Published: (2025)

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning
by: Liu, Wenpu, et al.
Published: (2026)

Heddle: A Distributed Orchestration System for Agentic RL Rollout
by: Zhang, Zili, et al.
Published: (2026)

Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEs
by: Zheng, Kaiwen, et al.
Published: (2023)

Learning from Less: SINDy Surrogates in RL
by: Dixit, Aniket, et al.
Published: (2025)

Momentum Particle Maximum Likelihood
by: Lim, Jen Ning, et al.
Published: (2023)

Dependency-aware Maximum Likelihood Estimation for Active Learning
by: Kalkanli, Beyza, et al.
Published: (2025)

Maximum Likelihood Learning of Latent Dynamics Without Reconstruction
by: Hromadka, Samo, et al.
Published: (2025)

BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning
by: Zhang, Xuechen, et al.
Published: (2025)

Combining Multi-Objective Bayesian Optimization with Reinforcement Learning for TinyML
by: Deutel, Mark, et al.
Published: (2023)

FBOS-RL: Feedback-Driven Bi-Objective Synergistic Reinforcement Learning
by: Zhang, Xikai, et al.
Published: (2026)

On Learning-Curve Monotonicity for Maximum Likelihood Estimators
by: Sellke, Mark, et al.
Published: (2025)

Selective Rollout: Mid-Trajectory Termination for Multi-Sample Agent RL
by: Zhai, Zhiyuan, et al.
Published: (2026)

Stable Training of Probabilistic Models Using the Leave-One-Out Maximum Log-Likelihood Objective
by: Bölat, Kutay, et al.
Published: (2023)

Contextual Rollout Bandits for Reinforcement Learning with Verifiable Rewards
by: Lu, Xiaodong, et al.
Published: (2026)

Hardness of Maximum Likelihood Learning of DPPs
by: Grigorescu, Elena, et al.
Published: (2022)

Bayesian Deployment Approval for Learned Landing Controllers under Finite Rollout Validation
by: Jiang, Fei, et al.
Published: (2026)

ImagineBench: Evaluating Reinforcement Learning with Large Language Model Rollouts
by: Pang, Jing-Cheng, et al.
Published: (2025)

Gradient-Informed Temporal Sampling Improves Rollout Accuracy in PDE Surrogate Training
by: Wang, Wenshuo, et al.
Published: (2026)

Recurrent Transformer U-Net Surrogate for Flow Modeling and Data Assimilation in Subsurface Formations with Faults
by: Han, Yifu, et al.
Published: (2025)

Diffusion World Model: Future Modeling Beyond Step-by-Step Rollout for Offline Reinforcement Learning
by: Ding, Zihan, et al.
Published: (2024)

BoreaRL: A Multi-Objective Reinforcement Learning Environment for Climate-Adaptive Boreal Forest Management
by: Dsouza, Kevin Bradley, et al.
Published: (2025)

Finite-Time Convergence and Sample Complexity of Actor-Critic Multi-Objective Reinforcement Learning
by: Zhou, Tianchen, et al.
Published: (2024)

SRT: Accelerating Reinforcement Learning via Speculative Rollout with Tree-Structured Cache
by: Chang, Chi-Chih, et al.
Published: (2026)

Scalable Inference-Time Annealing with Surrogate Likelihood Estimators
by: Peñaherrera, Daniel, et al.
Published: (2026)

When Demonstrations Meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning
by: Zeng, Siliang, et al.
Published: (2023)

QaRL: Rollout-Aligned Quantization-Aware RL for Fast and Stable Training under Training--Inference Mismatch
by: Gu, Hao, et al.
Published: (2026)