中文
相关论文

相关论文: Provable Benefits of Multi-task RL under Non-Marko…

200 篇论文

Meta-reinforcement learning (meta-RL) is a promising framework for tackling challenging domains requiring efficient exploration. Existing meta-RL algorithms are characterized by low sample efficiency, and mostly focus on low-dimensional…

机器学习 · 计算机科学 2024-03-18 Zohar Rimon , Tom Jurgenson , Orr Krupnik , Gilad Adler , Aviv Tamar

Constructing useful representations across a large number of tasks is a key requirement for sample-efficient intelligent systems. A traditional idea in multitask learning (MTL) is building a shared representation across tasks which can then…

机器学习 · 计算机科学 2023-03-09 Yingcong Li , Samet Oymak

This paper explores the effect of using multitask learning for abstractive summarization in the context of small training corpora. In particular, we incorporate four different tasks (extractive summarization, language modeling, concept…

计算与语言 · 计算机科学 2021-09-20 Ahmed Magooda , Mohamed Elaraby , Diane Litman

We study reward-free reinforcement learning (RL) with linear function approximation, where the agent works in two phases: (1) in the exploration phase, the agent interacts with the environment but cannot access the reward; and (2) in the…

机器学习 · 计算机科学 2024-02-15 Junkai Zhang , Weitong Zhang , Quanquan Gu

Reinforcement Learning (RL) has demonstrated a huge potential in learning optimal policies without any prior knowledge of the process to be controlled. Model Predictive Control (MPC) is a popular control technique which is able to deal with…

系统与控制 · 计算机科学 2019-04-10 Mario Zanon , Sébastien Gros , Alberto Bemporad

When faced with learning a set of inter-related tasks from a limited amount of usable data, learning each task independently may lead to poor generalization performance. Multi-Task Learning (MTL) exploits the latent relations between tasks…

机器学习 · 计算机科学 2015-08-14 Niloofar Yousefi , Michael Georgiopoulos , Georgios C. Anagnostopoulos

Reinforcement learning (RL) in large environments often suffers from severe computational bottlenecks, as conventional regret minimization algorithms require repeated, costly calls to planning and statistical estimation oracles. While…

机器学习 · 计算机科学 2026-05-04 Haichen Hu , Jian Qian , David Simchi-Levi

Multi-task learning has the potential to improve generalization by maximizing positive transfer between tasks while reducing task interference. Fully achieving this potential is hindered by manually designed architectures that remain static…

机器学习 · 计算机科学 2023-05-02 Naresh Kumar Gurulingan , Bahram Zonooz , Elahe Arani

We study the offline data-driven sequential decision making problem in the framework of Markov decision process (MDP). In order to enhance the generalizability and adaptivity of the learned policy, we propose to evaluate each policy by a…

统计理论 · 数学 2021-11-11 Zhengling Qi , Peng Liao

The fields of MPC and RL consider two successful control techniques for Markov decision processes. Both approaches are derived from similar fundamental principles, and both are widely used in practical applications, including robotics,…

Doubly robust methods hold considerable promise for off-policy evaluation in Markov decision processes (MDPs) under sequential ignorability: They have been shown to converge as $1/\sqrt{T}$ with the horizon $T$, to be statistically…

机器学习 · 统计学 2025-09-30 Mohammad Mehrabi , Stefan Wager

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

Large language models (LLMs) have shown promise in performing complex multi-step reasoning, yet they continue to struggle with mathematical reasoning, often making systematic errors. A promising solution is reinforcement learning (RL)…

机器学习 · 计算机科学 2025-09-22 Hanning Zhang , Pengcheng Wang , Shizhe Diao , Yong Lin , Rui Pan , Hanze Dong , Dylan Zhang , Pavlo Molchanov , Tong Zhang

Partial observability is a notorious challenge in reinforcement learning (RL), due to the need to learn complex, history-dependent policies. Recent empirical successes have used privileged expert distillation--which leverages availability…

机器学习 · 计算机科学 2025-10-06 Yuda Song , Dhruv Rohatgi , Aarti Singh , J. Andrew Bagnell

Reward-free reinforcement learning (RL) considers the setting where the agent does not have access to a reward function during exploration, but must propose a near-optimal policy for an arbitrary reward function revealed only after…

机器学习 · 计算机科学 2022-06-22 Andrew Wagenmaker , Yifang Chen , Max Simchowitz , Simon S. Du , Kevin Jamieson

Safety is a fundamental challenge in reinforcement learning (RL), particularly in real-world applications such as autonomous driving, robotics, and healthcare. To address this, Constrained Markov Decision Processes (CMDPs) are commonly used…

机器学习 · 计算机科学 2026-02-18 Chang Liu , Yunfan Li , Lin F. Yang

We consider primal-dual-based reinforcement learning (RL) in episodic constrained Markov decision processes (CMDPs) with non-stationary objectives and constraints, which plays a central role in ensuring the safety of RL in time-varying…

机器学习 · 计算机科学 2022-11-22 Yuhao Ding , Javad Lavaei

In recent years, meta-reinforcement learning (meta-RL) algorithm has been proposed to improve sample efficiency in the field of decision-making and control, enabling agents to learn new knowledge from a small number of samples. However,…

机器学习 · 计算机科学 2025-01-14 Chenyang Qi , Huiping Li , Panfeng Huang

Batch reinforcement learning (RL) is important to apply RL algorithms to many high stakes tasks. Doing batch RL in a way that yields a reliable new policy in large domains is challenging: a new decision policy may visit states and actions…

机器学习 · 计算机科学 2020-07-23 Yao Liu , Adith Swaminathan , Alekh Agarwal , Emma Brunskill

The aim of multi-task reinforcement learning is two-fold: (1) efficiently learn by training against multiple tasks and (2) quickly adapt, using limited samples, to a variety of new tasks. In this work, the tasks correspond to reward…

机器学习 · 计算机科学 2019-11-05 Nicholas C. Landolfi , Garrett Thomas , Tengyu Ma
‹ 上一页 1 8 9 10 下一页 ›