English
Related papers

Related papers: How Neural Reward Models Learn Features for Policy…

200 papers

Current reinforcement learning from human feedback (RLHF) pipelines for large language model (LLM) alignment typically assign scalar rewards to sequences, using the final token as a surrogate indicator for the quality of the entire…

Machine Learning · Computer Science 2025-04-24 Ryan Koo , Ian Yang , Vipul Raheja , Mingyi Hong , Kwang-Sung Jun , Dongyeop Kang

We consider the problem of sequentially making decisions that are rewarded by "successes" and "failures" which can be predicted through an unknown relationship that depends on a partially controllable vector of attributes for each instance.…

Machine Learning · Statistics 2017-09-18 Yingfei Wang , Chu Wang , Warren Powell

Learning to make decisions from observed data in dynamic environments remains a problem of fundamental importance in a number of fields, from artificial intelligence and robotics, to medicine and finance. This paper concerns the problem of…

Machine Learning · Statistics 2018-06-04 Jack Umenberger , Thomas B. Schön

Nonparametric regression with random design is considered. Estimates are defined by minimzing a penalized empirical $L_2$ risk over a suitably chosen class of neural networks with one hidden layer via gradient descent. Here, the gradient…

Statistics Theory · Mathematics 2019-12-10 Alina Braun , Michael Kohler , Harro Walk

Agents that can learn to imitate given video observation -- \emph{without direct access to state or action information} are more applicable to learning in the natural world. However, formulating a reinforcement learning (RL) agent that…

Machine Learning · Computer Science 2023-07-14 Glen Berseth , Florian Golemo , Christopher Pal

We introduce the forward-backward (FB) representation of the dynamics of a reward-free Markov decision process. It provides explicit near-optimal policies for any reward specified a posteriori. During an unsupervised phase, we use…

Machine Learning · Computer Science 2021-10-12 Ahmed Touati , Yann Ollivier

Aligning large language models (LLMs) with human preferences through reinforcement learning (RLHF) can lead to reward hacking, where LLMs exploit failures in the reward model (RM) to achieve seemingly high rewards without meeting the…

Machine Learning · Computer Science 2024-01-23 Alexandre Ramé , Nino Vieillard , Léonard Hussenot , Robert Dadashi , Geoffrey Cideron , Olivier Bachem , Johan Ferret

Training language models via reinforcement learning often relies on imperfect proxy rewards, since ground truth rewards that precisely define the intended behavior are rarely available. Standard metrics for assessing the quality of proxy…

Machine Learning · Computer Science 2026-04-29 Shuning Shang , Hubert Strauss , Stanley Wei , Sanjeev Arora , Noam Razin

Reinforcement learning consists of finding policies that maximize an expected cumulative long-term reward in a Markov decision process with unknown transition probabilities and instantaneous rewards. In this paper, we consider the problem…

Systems and Control · Computer Science 2018-07-31 Santiago Paternain , Juan Andrés Bazerque , Austin Small , Alejandro Ribeiro

We study the first gradient descent step on the first-layer parameters $\boldsymbol{W}$ in a two-layer neural network: $f(\boldsymbol{x}) = \frac{1}{\sqrt{N}}\boldsymbol{a}^\top\sigma(\boldsymbol{W}^\top\boldsymbol{x})$, where…

Machine Learning · Statistics 2022-05-04 Jimmy Ba , Murat A. Erdogdu , Taiji Suzuki , Zhichao Wang , Denny Wu , Greg Yang

Imitation learning is well-suited for robotic tasks where it is difficult to directly program the behavior or specify a cost for optimal control. In this work, we propose a method for learning the reward function (and the corresponding…

Machine Learning · Computer Science 2021-01-01 Tianwei Ni , Harshit Sikchi , Yufei Wang , Tejus Gupta , Lisa Lee , Benjamin Eysenbach

Manipulating data, such as weighting data examples or augmenting with new instances, has been increasingly used to improve model training. Previous work has studied various rule- or learning-based approaches designed for specific types of…

Machine Learning · Computer Science 2019-10-29 Zhiting Hu , Bowen Tan , Ruslan Salakhutdinov , Tom Mitchell , Eric P. Xing

Learning to evaluate and improve policies is a core problem of Reinforcement Learning (RL). Traditional RL algorithms learn a value function defined for a single policy. A recently explored competitive alternative is to learn a single value…

Machine Learning · Computer Science 2022-07-05 Francesco Faccio , Aditya Ramesh , Vincent Herrmann , Jean Harb , Jürgen Schmidhuber

Reinforcement learning (RL), a common tool in decision making, learns control policies from various experiences based on the associated cumulative return/rewards without treating them differently. Humans, on the contrary, often learn to…

Machine Learning · Computer Science 2025-11-25 Mingkang Wu , Devin White , Vernon Lawhern , Nicholas R. Waytowich , Yongcan Cao

The objective of a reinforcement learning agent is to behave so as to maximise the sum of a suitable scalar function of state: the reward. These rewards are typically given and immutable. In this paper, we instead consider the proposition…

Artificial Intelligence · Computer Science 2020-08-25 Zeyu Zheng , Junhyuk Oh , Matteo Hessel , Zhongwen Xu , Manuel Kroiss , Hado van Hasselt , David Silver , Satinder Singh

Policy gradient based reinforcement learning algorithms coupled with neural networks have shown success in learning complex policies in the model free continuous action space control setting. However, explicitly parameterized policies are…

Machine Learning · Computer Science 2019-09-30 Oliver Richter , Roger Wattenhofer

In reinforcement learning from human feedback, it is common to optimize against a reward model trained to predict human preferences. Because the reward model is an imperfect proxy, optimizing its value too much can hinder ground truth…

Machine Learning · Computer Science 2022-10-20 Leo Gao , John Schulman , Jacob Hilton

An artificial neural network can be trained by uniformly broadcasting a reward signal to units that implement a REINFORCE learning rule. Though this presents a biologically plausible alternative to backpropagation in training a network, the…

Machine Learning · Computer Science 2021-12-23 Stephen Chung

A key challenge in reward learning from human input is that desired agent behavior often changes based on context. For example, a robot must adapt to avoid a stove once it becomes hot. We observe that while high-level preferences (e.g.,…

Robotics · Computer Science 2026-01-14 Alexandra Forsey-Smerek , Julie Shah , Andreea Bobu

Inverse reinforcement learning (IRL) seeks to learn the reward function from expert trajectories, to understand the task for imitation or collaboration thereby removing the need for manual reward engineering. However, IRL in the context of…

Machine Learning · Computer Science 2023-11-13 Yikang Gui , Prashant Doshi