English
Related papers

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

200 papers

Commonly in reinforcement learning (RL), rewards are discounted over time using an exponential function to model time preference, thereby bounding the expected long-term reward. In contrast, in economics and psychology, it has been shown…

Machine Learning · Computer Science 2022-12-08 Matthias Schultheis , Constantin A. Rothkopf , Heinz Koeppl

Reward specification is one of the most tricky problems in Reinforcement Learning, which usually requires tedious hand engineering in practice. One promising approach to tackle this challenge is to adopt existing expert video demonstrations…

Artificial Intelligence · Computer Science 2024-11-05 Yuwei Fu , Haichao Zhang , Di Wu , Wei Xu , Benoit Boulet

In this paper we analyze the $L_2$ error of neural network regression estimates with one hidden layer. Under the assumption that the Fourier transform of the regression function decays suitably fast, we show that an estimate, where all…

Statistics Theory · Mathematics 2023-08-21 Alina Braun , Michael Kohler , Sophie Langer , Harro Walk

Latent diffusion models are the state-of-the-art for synthetic image generation. To align these models with human preferences, training the models using reinforcement learning on human feedback is crucial. Black et. al 2024 introduced…

Machine Learning · Computer Science 2024-04-09 Mo Kordzanganeh , Danial Keshvary , Nariman Arian

On a variety of tasks, the performance of neural networks predictably improves with training time, dataset size and model size across many orders of magnitude. This phenomenon is known as a neural scaling law. Of fundamental importance is…

Machine Learning · Statistics 2024-06-25 Blake Bordelon , Alexander Atanasov , Cengiz Pehlevan

The goal of inverse reinforcement learning (IRL) is to infer a reward function that explains the behavior of an agent performing a task. The assumption that most approaches make is that the demonstrated behavior is near-optimal. In many…

Machine Learning · Computer Science 2020-11-20 Luis Haug , Ivan Ovinnikov , Eugene Bykovets

Bandit optimization is a difficult problem, especially if the reward model is high-dimensional. When rewards are modeled by neural networks, sublinear regret has only been shown under strong assumptions, usually when the network is…

Machine Learning · Computer Science 2025-01-14 Mikhail Terekhov

It is commonly believed that optimizing the reverse KL divergence results in "mode seeking", while optimizing forward KL results in "mass covering", with the latter being preferred if the goal is to sample from multiple diverse modes. We…

Machine Learning · Computer Science 2025-10-24 Anthony GX-Chen , Jatin Prakash , Jeff Guo , Rob Fergus , Rajesh Ranganath

In some agent designs like inverse reinforcement learning an agent needs to learn its own reward function. Learning the reward function and optimising for it are typically two different processes, usually performed at different stages. We…

Artificial Intelligence · Computer Science 2020-04-29 Stuart Armstrong , Jan Leike , Laurent Orseau , Shane Legg

Reinforcement learning for LLMs is vulnerable to reward hacking, where models exploit shortcuts to maximize reward without solving the intended task. We systematically study this phenomenon in coding tasks using an environment-manipulation…

Machine Learning · Computer Science 2026-04-03 Rui Wu , Ruixiang Tang

Reinforcement fine-tuning (RFT) often suffers from reward over-optimization, where a policy model hacks the reward signals to achieve high scores while producing low-quality outputs. Our theoretical analysis shows that the key lies in…

In computational reinforcement learning, a growing body of work seeks to construct an agent's perception of the world through predictions of future sensations; predictions about environment observations are used as additional input features…

Machine Learning · Computer Science 2022-06-15 Alexandra Kearney , Anna Koop , Johannes Günther , Patrick M. Pilarski

Aligning large language models (LLMs) to preference data typically assumes a known link function between observed preferences and latent rewards (e.g., a logistic Bradley-Terry link). Misspecification of this link can bias inferred rewards…

Machine Learning · Computer Science 2026-02-03 Nathan Kallus

Sparse reward problems are one of the biggest challenges in Reinforcement Learning. Goal-directed tasks are one such sparse reward problems where a reward signal is received only when the goal is reached. One promising way to train an agent…

Machine Learning · Computer Science 2018-11-06 Ameet Deshpande , Srikanth Sarma , Ashutosh Jha , Balaraman Ravindran

Goal-Conditioned Reinforcement Learning (RL) problems often have access to sparse rewards where the agent receives a reward signal only when it has achieved the goal, making policy optimization a difficult problem. Several works augment…

Machine Learning · Computer Science 2023-10-11 Siddhant Agarwal , Ishan Durugkar , Peter Stone , Amy Zhang

In reinforcement learning (RL), different reward functions can define the same optimal policy but result in drastically different learning performance. For some, the agent gets stuck with a suboptimal behavior, and for others, it solves the…

Machine Learning · Computer Science 2025-02-25 Grigorii Veviurko , Wendelin Böhmer , Mathijs de Weerdt

A reliable reward model is essential for aligning large language models with human preferences through reinforcement learning from human feedback. However, standard reward models are susceptible to spurious features that are not causally…

Machine Learning · Computer Science 2026-05-19 Yupei Yang , Lin Yang , Wanxi Deng , Lin Qu , Fan Feng , Biwei Huang , Shikui Tu , Lei Xu

In reinforcement learning, specifying reward functions that capture the intended task can be very challenging. Reward learning aims to address this issue by learning the reward function. However, a learned reward model may have a low error…

Machine Learning · Computer Science 2025-07-09 Lukas Fluri , Leon Lang , Alessandro Abate , Patrick Forré , David Krueger , Joar Skalse

Self-reflection capabilities emerge in Large Language Models after RL post-training, with multi-turn RL achieving substantial gains over SFT counterparts. Yet the mechanism of how a unified optimization objective gives rise to functionally…

Machine Learning · Computer Science 2026-04-13 Zibo Zhao , Yuanting Zha , Haipeng Zhang , Xingcheng Xu

In this paper, we tackle the challenging problem of delayed rewards in reinforcement learning (RL). While Proximal Policy Optimization (PPO) has emerged as a leading Policy Gradient method, its performance can degrade under delayed rewards.…

‹ Prev 1 4 5 6 7 8 10 Next ›