中文
相关论文

相关论文: ReLOAD: Reinforcement Learning with Optimistic Asc…

200 篇论文

Reinforcement Learning (RL) has shown exceptional performance across various applications, enabling autonomous agents to learn optimal policies through interaction with their environments. However, traditional RL frameworks often face…

机器学习 · 计算机科学 2025-09-03 Rui Liu , Anish Gupta , Erfaun Noorani , Pratap Tokekar

This paper focuses on the critical load restoration problem in distribution systems following major outages. To provide fast online response and optimal sequential decision-making support, a reinforcement learning (RL) based approach is…

系统与控制 · 电气工程与系统科学 2024-01-30 Xiangyu Zhang , Abinet Tesfaye Eseye , Bernard Knueven , Weijia Liu , Matthew Reynolds , Wesley Jones

Inverse Constrained Reinforcement Learning (ICRL) is the task of inferring the implicit constraints that expert agents adhere to, based on their demonstration data. As an emerging research topic, ICRL has received considerable attention in…

机器学习 · 计算机科学 2025-02-04 Guiliang Liu , Sheng Xu , Shicheng Liu , Ashish Gaurav , Sriram Ganapathi Subramanian , Pascal Poupart

The optimal objective is a fundamental aspect of reinforcement learning (RL), as it determines how policies are evaluated and optimized. While total return maximization is the ideal objective in RL, discounted return maximization is the…

机器学习 · 计算机科学 2025-03-19 Shuyu Yin , Fei Wen , Peilin Liu , Tao Luo

Off-road navigation on vertically challenging terrain, involving steep slopes and rugged boulders, presents significant challenges for wheeled robots both at the planning level to achieve smooth collision-free trajectories and at the…

机器人学 · 计算机科学 2024-10-29 Tong Xu , Chenhui Pan , Xuesu Xiao

Various methods for solving the inverse reinforcement learning (IRL) problem have been developed independently in machine learning and economics. In particular, the method of Maximum Causal Entropy IRL is based on the perspective of entropy…

机器学习 · 计算机科学 2021-03-05 Navyata Sanghvi , Shinnosuke Usami , Mohit Sharma , Joachim Groeger , Kris Kitani

Designing and analyzing model-based RL (MBRL) algorithms with guaranteed monotonic improvement has been challenging, mainly due to the interdependence between policy optimization and model learning. Existing discrepancy bounds generally…

机器学习 · 计算机科学 2023-11-09 Tianying Ji , Yu Luo , Fuchun Sun , Mingxuan Jing , Fengxiang He , Wenbing Huang

We study reinforcement learning (RL) in the agnostic policy learning setting, where the goal is to find a policy whose performance is competitive with the best policy in a given class of interest $\Pi$ -- crucially, without assuming that…

机器学习 · 计算机科学 2025-07-08 Uri Sherman , Tomer Koren , Yishay Mansour

In many RL applications, ensuring an agent's actions adhere to constraints is crucial for safety. Most previous methods in Action-Constrained Reinforcement Learning (ACRL) employ a projection layer after the policy network to correct the…

机器学习 · 计算机科学 2025-02-18 Janaka Chathuranga Brahmanage , Jiajing Ling , Akshat Kumar

We study the reinforcement learning (RL) problem in a constrained Markov decision process (CMDP), where an agent explores the environment to maximize the expected cumulative reward while satisfying a single constraint on the expected total…

Action-constrained reinforcement learning (ACRL) is a generic framework for learning control policies with zero action constraint violation, which is required by various safety-critical and resource-constrained applications. The existing…

机器学习 · 计算机科学 2025-03-18 Wei Hung , Shao-Hua Sun , Ping-Chun Hsieh

Solving long-horizon goal-conditioned tasks remains a significant challenge in reinforcement learning (RL). Hierarchical reinforcement learning (HRL) addresses this by decomposing tasks into more manageable sub-tasks, but the automatic…

机器学习 · 计算机科学 2025-09-09 Yang Yu

Many real-world applications can be formulated as multi-agent cooperation problems, such as network packet routing and coordination of autonomous vehicles. The emergence of deep reinforcement learning (DRL) provides a promising approach for…

多智能体系统 · 计算机科学 2022-06-28 Zhixuan Liang , Jiannong Cao , Shan Jiang , Divya Saxena , Huafeng Xu

Reinforcement Learning (RL) has achieved state-of-the-art results in domains such as robotics and games. We build on this previous work by applying RL algorithms to a selection of canonical online stochastic optimization problems with a…

Reinforcement learning (RL) allows an agent interacting sequentially with an environment to maximize its long-term expected return. In the distributional RL (DistrRL) paradigm, the agent goes beyond the limit of the expected value, to…

机器学习 · 计算机科学 2023-05-01 Mastane Achab , Reda Alami , Yasser Abdelaziz Dahou Djilali , Kirill Fedyanin , Eric Moulines

Many traditional algorithms for solving combinatorial optimization problems involve using hand-crafted heuristics that sequentially construct a solution. Such heuristics are designed by domain experts and may often be suboptimal due to the…

机器学习 · 计算机科学 2020-12-25 Nina Mazyavkina , Sergey Sviridov , Sergei Ivanov , Evgeny Burnaev

Reinforcement learning (RL) presents a promising framework to learn policies through environment interaction, but often requires an infeasible amount of interaction data to solve complex tasks from sparse rewards. One direction includes…

机器学习 · 计算机科学 2024-05-07 Stone Tao , Arth Shukla , Tse-kai Chan , Hao Su

Continuous-time nonlinear optimal control problems hold great promise in real-world applications. After decades of development, reinforcement learning (RL) has achieved some of the greatest successes as a general nonlinear control design…

系统与控制 · 电气工程与系统科学 2023-07-19 Brent A. Wallace , Jennie Si

Reinforcement learning (RL) requires skillful definition and remarkable computational efforts to solve optimization and control problems, which could impair its prospect. Introducing human guidance into reinforcement learning is a promising…

机器学习 · 计算机科学 2022-11-30 Jingda Wu , Zhiyu Huang , Wenhui Huang , Chen Lv

In this paper, we study a novel episodic risk-sensitive Reinforcement Learning (RL) problem, named Iterated CVaR RL, which aims to maximize the tail of the reward-to-go at each step, and focuses on tightly controlling the risk of getting…

机器学习 · 计算机科学 2023-05-12 Yihan Du , Siwei Wang , Longbo Huang