中文
相关论文

相关论文: Group Effect Enhanced Generative Adversarial Imita…

200 篇论文

Many modern methods for imitation learning and inverse reinforcement learning, such as GAIL or AIRL, are based on an adversarial formulation. These methods apply GANs to match the expert's distribution over states and actions with the…

机器学习 · 计算机科学 2020-08-11 Oleg Arenz , Gerhard Neumann

Interactive-Grounded Learning (IGL) [Xie et al., 2021] is a powerful framework in which a learner aims at maximizing unobservable rewards through interacting with an environment and observing reward-dependent feedback on the taken actions.…

机器学习 · 计算机科学 2024-06-03 Mengxiao Zhang , Yuheng Zhang , Haipeng Luo , Paul Mineiro

Recently, a simple yet effective algorithm -- goal-conditioned supervised-learning (GCSL) -- was proposed to tackle goal-conditioned reinforcement-learning. GCSL is based on the principle of hindsight learning: by observing states visited…

机器学习 · 计算机科学 2023-05-18 Tom Jurgenson , Aviv Tamar

Making decisions in complex driving environments is a challenging task for autonomous agents. Imitation learning methods have great potentials for achieving such a goal. Adversarial Inverse Reinforcement Learning (AIRL) is one of the…

人工智能 · 计算机科学 2021-03-29 Pin Wang , Dapeng Liu , Jiayu Chen , Hanhan Li , Ching-Yao Chan

We propose a new method for event extraction (EE) task based on an imitation learning framework, specifically, inverse reinforcement learning (IRL) via generative adversarial network (GAN). The GAN estimates proper rewards according to the…

计算与语言 · 计算机科学 2018-04-24 Tongtao Zhang , Heng Ji

Increasingly large trip demands have strained urban transportation capacity, which consequently leads to traffic congestion and rapid growth of greenhouse gas emissions. In this work, we focus on achieving sustainable transportation by…

计算机与社会 · 计算机科学 2019-12-09 Luyao Niu , Andrew Clark

Complex planning and scheduling problems have long been solved using various optimization or heuristic approaches. In recent years, imitation learning that aims to learn from expert demonstrations has been proposed as a viable alternative…

机器学习 · 计算机科学 2024-05-24 Qian Shao , Pradeep Varakantham , Shih-Fen Cheng

Estimating the travel time of a path is an essential topic for intelligent transportation systems. It serves as the foundation for real-world applications, such as traffic monitoring, route planning, and taxi dispatching. However, building…

机器学习 · 计算机科学 2022-07-05 Zhiwen Zhang , Hongjun Wang , Jiyuan Chen , Zipei Fan , Xuan Song , Ryosuke Shibasaki

With the widespread adoption of electric vehicles (EVs), navigating for EV drivers to select a cost-effective charging station has become an important yet challenging issue due to dynamic traffic conditions, fluctuating electricity prices,…

机器学习 · 计算机科学 2025-02-28 Tianyang Qi , Shibo Chen , Jun Zhang

Critical sectors of human society are progressing toward the adoption of powerful artificial intelligence (AI) agents, which are trained individually on behalf of self-interested principals but deployed in a shared environment. Short of…

多智能体系统 · 计算机科学 2021-12-22 Jiachen Yang , Ethan Wang , Rakshit Trivedi , Tuo Zhao , Hongyuan Zha

Imitation learning holds great promise for addressing the complex task of autonomous urban driving, as experienced human drivers can navigate highly challenging scenarios with ease. While behavior cloning is a widely used imitation learning…

机器人学 · 计算机科学 2023-05-05 Ke Guo , Wei Jing , Junbo Chen , Jia Pan

The goal of this paper is to study a distributed version of the gradient temporal-difference (GTD) learning algorithm for a class of multi-agent Markov decision processes (MDPs). The temporal-difference (TD) learning is a reinforcement…

最优化与控制 · 数学 2020-04-29 Donghwan Lee , Jianghai Hu

An efficient and reliable multi-agent decision-making system is highly demanded for the safe and efficient operation of connected autonomous vehicles in intelligent transportation systems. Current researches mainly focus on the Deep…

机器人学 · 计算机科学 2022-02-01 Qi Liu , Zirui Li , Xueyuan Li , Jingda Wu , Shihua Yuan

Individuals undertake both solo and joint activities as part of their overall activity-travel patterns. Compared to work and maintenance activities, social and leisure activities differ in that they exhibit high levels of temporal and…

社会与信息网络 · 计算机科学 2023-08-08 Chenglin Han , Lichen Luo , Giancarlos Parady , Kiyoshi Takami , Makoto Chikaraishi , Noboru Harata

Stabilizing cooperation among self-interested individuals presents a fundamental challenge in evolutionary theory and social science. While classical models predict the dominance of defection in social dilemmas, empirical and theoretical…

物理与社会 · 物理学 2025-04-08 Pierre Bousseyroux , Gilles Zérah , Michael Benzaquen

Cell-free multiple-input multiple-output (CF-MIMO) architecture significantly enhances wireless network performance, offering a promising solution for delay-sensitive applications. This paper investigates the resource allocation problem in…

信息论 · 计算机科学 2026-04-24 Shuangbo Xiong , Cheng Zhang , Wen Wang , Wenwu Yu , Yongming Huang

As urban residents demand higher travel quality, vehicle dispatch has become a critical component of online ride-hailing services. However, current vehicle dispatch systems struggle to navigate the complexities of urban traffic dynamics,…

机器学习 · 计算机科学 2024-12-17 Xiao Han , Zijian Zhang , Xiangyu Zhao , Yuanshao Zhu , Guojiang Shen , Xiangjie Kong , Xuetao Wei , Liqiang Nie , Jieping Ye

Approaches based on generative adversarial networks for imitation learning are promising because they are sample efficient in terms of expert demonstrations. However, training a generator requires many interactions with the actual…

机器学习 · 计算机科学 2022-09-01 Eiji Uchibe

In multi-agent reinforcement learning (MARL), it is challenging for a collection of agents to learn complex temporally extended tasks. The difficulties lie in computational complexity and how to learn the high-level ideas behind reward…

多智能体系统 · 计算机科学 2021-10-04 Jueming Hu , Zhe Xu , Weichang Wang , Guannan Qu , Yutian Pang , Yongming Liu

Cross-domain imitation learning studies how to leverage expert demonstrations of one agent to train an imitation agent with a different embodiment or morphology. Comparing trajectories and stationary distributions between the expert and…

机器学习 · 计算机科学 2026-01-14 Arnaud Fickinger , Samuel Cohen , Stuart Russell , Brandon Amos