中文
相关论文

相关论文: Universal Reinforcement Learning

200 篇论文

To achieve general intelligence, agents must learn how to interact with others in a shared environment: this is the challenge of multiagent reinforcement learning (MARL). The simplest form is independent reinforcement learning (InRL), where…

We consider reinforcement learning (RL) in Markov Decision Processes in which an agent repeatedly interacts with an environment that is modeled by a controlled Markov process. At each time step $t$, it earns a reward, and also incurs a…

机器学习 · 计算机科学 2023-03-16 Rahul Singh , Abhishek Gupta , Ness B. Shroff

Empowerment quantifies the influence an agent has on its environment. This is formally achieved by the maximum of the expected KL-divergence between the distribution of the successor state conditioned on a specific action and a distribution…

机器学习 · 统计学 2015-09-29 Maximilian Karl , Justin Bayer , Patrick van der Smagt

Reinforcement Learning, a machine learning framework for training an autonomous agent based on rewards, has shown outstanding results in various domains. However, it is known that learning a good policy is difficult in a domain where…

机器学习 · 计算机科学 2019-06-27 Takahisa Imagawa , Takuya Hiraoka , Yoshimasa Tsuruoka

In reinforcement learning (RL), agents often operate in partially observed and uncertain environments. Model-based RL suggests that this is best achieved by learning and exploiting a probabilistic model of the world. 'Active inference' is…

机器学习 · 计算机科学 2019-11-26 Alexander Tschantz , Manuel Baltieri , Anil. K. Seth , Christopher L. Buckley

Learning algorithms are often used to make decisions in sequential decision-making environments. In multi-agent settings, the decisions of each agent can affect the utilities/losses of the other agents. Therefore, if an agent is good at…

计算机科学与博弈论 · 计算机科学 2024-07-09 Angelos Assos , Yuval Dagan , Constantinos Daskalakis

Efficient probabilistic inference by variable elimination in graphical models requires an optimal elimination order. However, finding an optimal order is a challenging combinatorial optimisation problem for models with a large number of…

人工智能 · 计算机科学 2025-03-13 Sagad Hamid , Tanya Braun

TAMER has proven to be a powerful interactive reinforcement learning method for allowing ordinary people to teach and personalize autonomous agents' behavior by providing evaluative feedback. However, a TAMER agent planning with UCT---a…

人工智能 · 计算机科学 2019-04-19 Guangliang Li , Randy Gomez , Keisuke Nakamura , Jinying Lin , Qilei Zhang , Bo He

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

The agency problem emerges in today's large scale machine learning tasks, where the learners are unable to direct content creation or enforce data collection. In this work, we propose a theoretical framework for aligning economic interests…

机器学习 · 计算机科学 2024-07-03 Jibang Wu , Siyu Chen , Mengdi Wang , Huazheng Wang , Haifeng Xu

Many real-world settings involve costs for performing actions; transaction costs in financial systems and fuel costs being common examples. In these settings, performing actions at each time step quickly accumulates costs leading to vastly…

机器学习 · 计算机科学 2023-06-06 David Mguni , Aivar Sootla , Juliusz Ziomek , Oliver Slumbers , Zipeng Dai , Kun Shao , Jun Wang

We study the problem of exploration in Reinforcement Learning and present a novel model-free solution. We adopt an information-theoretical viewpoint and start from the instance-specific lower bound of the number of samples that have to be…

机器学习 · 计算机科学 2024-07-02 Alessio Russo , Alexandre Proutiere

Most of the existing learning models, particularly deep neural networks, are reliant on large datasets whose hand-labeling is expensive and time demanding. A current trend is to make the learning of these models frugal and less dependent on…

计算机视觉与模式识别 · 计算机科学 2022-12-12 Sebastien Deschamps , Hichem Sahbi

Robots that navigate among pedestrians use collision avoidance algorithms to enable safe and efficient operation. Recent works present deep reinforcement learning as a framework to model the complex interactions and cooperation. However,…

机器人学 · 计算机科学 2018-05-08 Michael Everett , Yu Fan Chen , Jonathan P. How

This paper studies safe Reinforcement Learning (safe RL) with linear function approximation and under hard instantaneous constraints where unsafe actions must be avoided at each step. Existing studies have considered safe RL with hard…

机器学习 · 计算机科学 2023-12-25 Honghao Wei , Xin Liu , Lei Ying

In standard Reinforcement Learning (RL) settings, the interaction between the agent and the environment is typically modeled as a Markov Decision Process (MDP), which assumes that the agent observes the system state instantaneously, selects…

机器学习 · 计算机科学 2025-06-18 John Wikman , Alexandre Proutiere , David Broman

We consider model-based multi-agent reinforcement learning, where the environment transition model is unknown and can only be learned via expensive interactions with the environment. We propose H-MARL (Hallucinated Multi-Agent Reinforcement…

机器学习 · 计算机科学 2022-07-12 Pier Giuseppe Sessa , Maryam Kamgarpour , Andreas Krause

In this paper, we propose a novel model-free reinforcement learning algorithm to compute the optimal policies for a multi-agent system with $N$ cooperative agents where each agent privately observes it's own private type and publicly…

系统与控制 · 电气工程与系统科学 2020-03-24 Rajesh K Mishra , Deepanshu Vasal , Sriram Vishwanath

In this paper we present our scientific discovery that good representation can be learned via continuous attention during the interaction between Unsupervised Learning(UL) and Reinforcement Learning(RL) modules driven by intrinsic…

机器学习 · 计算机科学 2019-04-03 Liang Zhao , Wei Xu

Optimal execution is a sequential decision-making problem for cost-saving in algorithmic trading. Studies have found that reinforcement learning (RL) can help decide the order-splitting sizes. However, a problem remains unsolved: how to…

交易与市场微观结构 · 定量金融 2022-07-25 Feiyang Pan , Tongzhe Zhang , Ling Luo , Jia He , Shuoling Liu