中文
相关论文

相关论文: Beyond Scalar Rewards: Distributional Reinforcemen…

200 篇论文

In this paper, we use concepts from supervisory control theory of discrete event systems to propose a method to learn optimal control policies for a finite-state Markov Decision Process (MDP) in which (only) certain sequences of actions are…

机器学习 · 计算机科学 2022-01-04 Arun Raman , Keerthan Shagrithaya , Shalabh Bhatnagar

Despite the numerous advances, reinforcement learning remains away from widespread acceptance for autonomous controller design as compared to classical methods due to lack of ability to effectively tackle the reality gap. The reliance on…

机器学习 · 计算机科学 2024-09-23 Narendra Patwardhan , Zequn Wang

Many reinforcement learning (RL) problems in practice are offline, learning purely from observational data. A key challenge is how to ensure the learned policy is safe, which requires quantifying the risk associated with different actions.…

机器学习 · 计算机科学 2021-10-28 Yecheng Jason Ma , Dinesh Jayaraman , Osbert Bastani

Reinforcement Learning (RL) is increasingly used in autonomous driving (AD) and shows clear advantages. However, most RL-based AD methods overlook policy structure design. An RL policy that only outputs short-timescale vehicle control…

机器人学 · 计算机科学 2025-11-25 Guizhe Jin , Zhuoren Li , Bo Leng , Ran Yu , Lu Xiong , Chen Sun

Enhancing diverse human decision-making processes in an urban environment is a critical issue across various applications, including ride-sharing vehicle dispatching, public transportation management, and autonomous driving. Offline…

机器学习 · 计算机科学 2024-06-21 Xinbo Zhao , Yingxue Zhang , Xin Zhang , Yu Yang , Yiqun Xie , Yanhua Li , Jun Luo

In this work, we propose a novel algorithmic framework for data sharing and coordinated exploration for the purpose of learning more data-efficient and better performing policies under a concurrent reinforcement learning (CRL) setting. In…

机器学习 · 统计学 2024-02-01 Tim Tse , Isaac Chan , Zhitang Chen

Reinforcement learning (RL) often necessitates a meticulous Markov Decision Process (MDP) design tailored to each task. This work aims to address this challenge by proposing a systematic approach to behavior synthesis and control for…

机器人学 · 计算机科学 2024-10-18 Jean-Pierre Sleiman , Mayank Mittal , Marco Hutter

We introduce a novel class of algorithms to efficiently approximate the unknown return distributions in policy evaluation problems from distributional reinforcement learning (DRL). The proposed distributional dynamic programming algorithms…

机器学习 · 统计学 2024-07-22 Julian Gerstenberg , Ralph Neininger , Denis Spiegel

As modern problems such as autonomous driving, control of robotic components, and medical diagnostics have become increasingly difficult to solve analytically, data-driven decision-making has seen a large gain in interest. Where there are…

机器学习 · 计算机科学 2022-09-27 Keith Badger

Due to its property of not requiring prior knowledge of the environment, reinforcement learning has significant potential for quantum control problems. In this work, we investigate the effectiveness of continuous control policies based on…

量子物理 · 物理学 2023-03-01 Shumin Zhou , Hailan Ma , Sen Kuang , Daoyi Dong

Reinforcement learning algorithms are typically designed for discrete-time dynamics, even though the underlying real-world control systems are often continuous in time. In this paper, we study the problem of continuous-time reinforcement…

机器学习 · 计算机科学 2026-03-03 Klemens Iten , Lenart Treven , Bhavya Sukhija , Florian Dörfler , Andreas Krause

Reinforcement learning (RL) offers significant promise for machinery fault detection (MFD). However, most existing RL-based MFD approaches do not fully exploit RL's sequential decision-making strengths, often treating MFD as a simple…

机器学习 · 计算机科学 2026-02-27 Dhiraj Neupane , Richard Dazeley , Mohamed Reda Bouadjenek , Sunil Aryal

Traditional trajectory planning methods for autonomous vehicles have several limitations. For example, heuristic and explicit simple rules limit generalizability and hinder complex motions. These limitations can be addressed using…

机器人学 · 计算机科学 2024-05-14 Hyunwoo Park

The goal of autonomous vehicles is to navigate public roads safely and comfortably. To enforce safety, traditional planning approaches rely on handcrafted rules to generate trajectories. Machine learning-based systems, on the other hand,…

Practical reinforcement learning problems are often formulated as constrained Markov decision process (CMDP) problems, in which the agent has to maximize the expected return while satisfying a set of prescribed safety constraints. In this…

机器学习 · 计算机科学 2019-09-23 Shin-ichi Maeda , Hayato Watahiki , Shintarou Okada , Masanori Koyama

Safe and efficient autonomous driving maneuvers in an interactive and complex environment can be considerably challenging due to the unpredictable actions of other surrounding agents that may be cooperative or adversarial in their…

机器人学 · 计算机科学 2019-01-28 Pin Wang , Ching-Yao Chan , Hanhan Li

Reinforcement Learning (RL) has gained substantial attention across diverse application domains and theoretical investigations. Existing literature on RL theory largely focuses on risk-neutral settings where the decision-maker learns to…

机器学习 · 计算机科学 2024-12-24 Zhengqi Wu , Renyuan Xu

The standard RL world model is that of a Markov Decision Process (MDP). A basic premise of MDPs is that the rewards depend on the last state and action only. Yet, many real-world rewards are non-Markovian. For example, a reward for bringing…

人工智能 · 计算机科学 2019-12-06 Maor Gaon , Ronen I. Brafman

Inverse reinforcement learning (IRL) and dynamic discrete choice (DDC) models explain sequential decision-making by recovering reward functions that rationalize observed behavior. Flexible IRL methods typically rely on machine learning but…

机器学习 · 计算机科学 2026-01-01 Lars van der Laan , Aurelien Bibaut , Nathan Kallus

Reinforcement Learning (RL) offers a powerful framework for optimizing dynamic treatment regimes (DTRs). However, clinical RL is fundamentally bottlenecked by reward engineering: the challenge of defining signals that safely and effectively…

机器学习 · 计算机科学 2026-02-05 Qianyi Xu , Gousia Habib , Feng Wu , Yanrui Du , Zhihui Chen , Swapnil Mishra , Dilruk Perera , Mengling Feng