中文
相关论文

相关论文: Guaranteeing Control Requirements via Reward Shapi…

200 篇论文

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…

机器学习 · 统计学 2018-06-04 Jack Umenberger , Thomas B. Schön

Deep reinforcement learning has proven remarkably useful in training agents from unstructured data. However, the opacity of the produced agents makes it difficult to ensure that they adhere to various requirements posed by human engineers.…

机器学习 · 计算机科学 2022-02-10 Raz Yerushalmi , Guy Amir , Achiya Elyasaf , David Harel , Guy Katz , Assaf Marron

Recently there has been a proliferation of intrinsic motivation (IM) reward-shaping methods to learn in complex and sparse-reward environments. These methods can often inadvertently change the set of optimal policies in an environment,…

While deep reinforcement learning techniques have led to agents that are successfully able to learn to perform a number of tasks that had been previously unlearnable, these techniques are still susceptible to the longstanding problem of…

人工智能 · 计算机科学 2019-11-05 Nicholas Waytowich , Sean L. Barton , Vernon Lawhern , Garrett Warnell

Reinforcement learning (RL) methods usually treat reward functions as black boxes. As such, these methods must extensively interact with the environment in order to discover rewards and optimal policies. In most RL applications, however,…

机器学习 · 计算机科学 2022-01-19 Rodrigo Toro Icarte , Toryn Q. Klassen , Richard Valenzano , Sheila A. McIlraith

Providing a suitable reward function to reinforcement learning can be difficult in many real world applications. While inverse reinforcement learning (IRL) holds promise for automatically learning reward functions from demonstrations,…

机器学习 · 计算机科学 2019-10-29 Lantao Yu , Tianhe Yu , Chelsea Finn , Stefano Ermon

Training robot manipulation policies is a challenging and open problem in robotics and artificial intelligence. In this paper we propose a novel and compact state representation based on the rewards predicted from an image-based task…

机器人学 · 计算机科学 2021-12-13 Cédérick Mouliets , Isabelle Ferrané , Heriberto Cuayáhuitl

Reinforcement learning has shown promise in learning policies that can solve complex problems. However, manually specifying a good reward function can be difficult, especially for intricate tasks. Inverse reinforcement learning offers a…

机器学习 · 计算机科学 2017-11-28 Peter Henderson , Wei-Di Chang , Pierre-Luc Bacon , David Meger , Joelle Pineau , Doina Precup

Teaching agents to follow complex written instructions has been an important yet elusive goal. One technique for enhancing learning efficiency is language reward shaping (LRS). Within a reinforcement learning (RL) framework, LRS involves…

人工智能 · 计算机科学 2023-08-21 Sukai Huang , Nir Lipovetzky , Trevor Cohn

Alignment is vital for safely deploying large language models (LLMs). Existing techniques are either reward-based (training a reward model on preference pairs and optimizing with reinforcement learning) or reward-free (directly fine-tuning…

计算与语言 · 计算机科学 2026-03-03 Ruoxi Cheng , Haoxuan Ma , Weixin Wang , Ranjie Duan , Jiexi Liu , Xiaoshuang Jia , Simeng Qin , Xiaochun Cao , Yang Liu , Xiaojun Jia

Several researchers have recently investigated the connection between reinforcement learning and classification. We are motivated by proposals of approximate policy iteration schemes without value functions which focus on policy…

机器学习 · 计算机科学 2008-07-06 Christos Dimitrakakis , Michail G. Lagoudakis

The aim of this paper is to study the reward based policy exploration problem in a supervised learning approach and enable robots to form complex movement trajectories in challenging reward settings and search spaces. For this, the…

机器人学 · 计算机科学 2020-11-10 M. Tuluhan Akbulut , Utku Bozdogan , Ahmet Tekden , Emre Ugur

In this paper, we develop a method for learning a control policy guaranteed to satisfy an affine state constraint of high relative degree in closed loop with a black-box system. Previous reinforcement learning (RL) approaches to satisfy…

系统与控制 · 电气工程与系统科学 2024-07-31 Jean-Baptiste Bouvier , Kartik Nagpal , Negar Mehr

Goal-conditioned reinforcement learning (RL) concerns the problem of training an agent to maximize the probability of reaching target goal states. This paper presents an analysis of the goal-conditioned setting based on optimal control. In…

机器学习 · 计算机科学 2026-05-15 Nathan P. Lawrence , Ali Mesbah

Existing alignment methods directly use the reward model learned from user preference data to optimize an LLM policy, subject to KL regularization with respect to the base policy. This practice is suboptimal for maximizing user's utility…

机器学习 · 计算机科学 2026-02-04 Haichuan Wang , Tao Lin , Lingkai Kong , Ce Li , Hezi Jiang , Milind Tambe

We consider an improper reinforcement learning setting where a learner is given $M$ base controllers for an unknown Markov decision process, and wishes to combine them optimally to produce a potentially new controller that can outperform…

机器学习 · 计算机科学 2021-07-06 Mohammadi Zaki , Avinash Mohan , Aditya Gopalan , Shie Mannor

Reinforcement-learning agents seek to maximize a reward signal through environmental interactions. As humans, our job in the learning process is to design reward functions to express desired behavior and enable the agent to learn such…

机器学习 · 计算机科学 2024-08-08 Zhiyuan Zhou , Shreyas Sundara Raman , Henry Sowerby , Michael L. Littman

Reinforcement learning suffers from limitations in real practices primarily due to the number of required interactions with virtual environments. It results in a challenging problem because we are implausible to obtain a local optimal…

机器学习 · 计算机科学 2024-10-28 Qizhen Wu , Kexin Liu , Lei Chen

A significant challenge in developing AI that can generalize well is designing agents that learn about their world without being told what to learn, and apply that learning to challenges with sparse rewards. Moreover, most traditional…

机器学习 · 计算机科学 2020-04-21 Eric Zelikman , William Yin , Kenneth Wang

Rewards play a crucial role in reinforcement learning. To arrive at the desired policy, the design of a suitable reward function often requires significant domain expertise as well as trial-and-error. Here, we aim to minimize the effort…

机器人学 · 计算机科学 2020-11-18 Zheng Wu , Wenzhao Lian , Vaibhav Unhelkar , Masayoshi Tomizuka , Stefan Schaal