paper-with-me

Papers

Maximum Likelihood Reinforcement Learning

2026-02-02 · Fahim Tajwar, Guanning Zeng, Yueer Zhou, Yuda Song, Daman Arora, Yiding Jiang, Jeff Schneider, Ruslan Salakhutdinov, Haiwen Feng, Andrea Zanette arxiv

Reinforcement learning (RL) is the method of choice for training models in setups where the objective function can only be evaluated by sampling from the model. Our key observation is that when the feedback is terminal and binary, models implicitly induce a likelihood over correct rollouts. Maximum likelihood would be the natural framework in such settings, but RL is used instead as a workaround to the non-differentiability. We prove that the standard, expected-reward RL formulation is only a first-order approximation of the likelihood. To remedy this mismatch, we introduce Maximum Likelihood Reinforcement Learning (MaxRL), a compute-indexed family of sample-based objectives that interpolate between expected-reward RL and maximum likelihood as sampling compute is scaled. The resulting objective is a one-line change to standard RL implementations. MaxRL Pareto-dominates existing methods in all tested models and tasks, achieves up to $20\times$ gains in test-time scaling efficiency over GRPO, and scales more favorably with additional training data and compute.

📄 PDF Abstract BibTeX arXiv:2602.02710

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningCode Generation

Similar Papers 제목 키워드 기반

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

2026-05-28 · Yifu Zheng arxiv

Correctness-based Reinforcement Learning with Verifiable Rewards (RLVR) trains language models from binary feedback on sampled outputs, but the objective optimized in expectation and the stochastic update geometry induce…

Reinforcement Learning

Maximum Likelihood Constraint Inference for Inverse Reinforcement Learning

2019-09-12 · ICLR 2020 1 · Dexter R. R. Scobee, S. Shankar Sastry

While most approaches to the problem of Inverse Reinforcement Learning (IRL) focus on estimating a reward function that best explains an expert agent's policy or demonstrated behavior on a control task, it is often the c…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Neural Math Word Problem Solver with Reinforcement Learning

2018-08-01 · COLING 2018 8 · Danqing Huang, Jing Liu, Chin-Yew Lin, Jian Yin

Sequence-to-sequence model has been applied to solve math word problems. The model takes math problem descriptions as input and generates equations as output. The advantage of sequence-to-sequence model requires no featu…

Feature EngineeringMathMath Word Problem Solvingreinforcement-learning+2

ARAML: A Stable Adversarial Training Framework for Text Generation

2019-08-20 · IJCNLP 2019 11 · Pei Ke, Fei Huang, Minlie Huang, Xiaoyan Zhu

Most of the existing generative adversarial networks (GAN) for text generation suffer from the instability of reinforcement learning training algorithms such as policy gradient, leading to unstable performance. To tackle…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Text Generation

The tree reconstruction game: phylogenetic reconstruction using reinforcement learning

2023-03-12 · Dana Azouri, Oz Granit, Michael Alburquerque, Yishay Mansour 외

We propose a reinforcement-learning algorithm to tackle the challenge of reconstructing phylogenetic trees. The search for the tree that best describes the data is algorithmically challenging, thus all current algorithms…

Q-Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)