中文
相关论文

相关论文: Beware of Instantaneous Dependence in Reinforcemen…

200 篇论文

Efficiently adapting to new environments and changes in dynamics is critical for agents to successfully operate in the real world. Reinforcement learning (RL) based approaches typically rely on external reward feedback for adaptation.…

机器学习 · 计算机科学 2019-03-05 Yuxiang Yang , Ken Caluwaerts , Atil Iscen , Jie Tan , Chelsea Finn

Accuracy and generalization of dynamics models is key to the success of model-based reinforcement learning (MBRL). As the complexity of tasks increases, so does the sample inefficiency of learning accurate dynamics models. However, many…

机器学习 · 计算机科学 2021-06-08 Manan Tomar , Amy Zhang , Roberto Calandra , Matthew E. Taylor , Joelle Pineau

We consider a context-dependent Reinforcement Learning (RL) setting, which is characterized by: a) an unknown finite number of not directly observable contexts; b) abrupt (discontinuous) context changes occurring during an episode; and c)…

机器学习 · 计算机科学 2022-02-15 Hang Ren , Aivar Sootla , Taher Jafferjee , Junxiao Shen , Jun Wang , Haitham Bou-Ammar

Many methods for Model-based Reinforcement learning (MBRL) in Markov decision processes (MDPs) provide guarantees for both the accuracy of the model they can deliver and the learning efficiency. At the same time, state abstraction…

机器学习 · 计算机科学 2023-11-16 Rolf A. N. Starre , Marco Loog , Elena Congeduti , Frans A. Oliehoek

Recently, safe reinforcement learning (RL) with the actor-critic structure for continuous control tasks has received increasing attention. It is still challenging to learn a near-optimal control policy with safety and convergence…

机器学习 · 计算机科学 2024-02-06 Xinglong Zhang , Yaoqian Peng , Biao Luo , Wei Pan , Xin Xu , Haibin Xie

Model-Based Reinforcement Learning (MBRL) offers a promising direction for sample efficient learning, often achieving state of the art results for continuous control tasks. However, many existing MBRL methods rely on combining greedy…

机器学习 · 计算机科学 2020-02-10 Philip Ball , Jack Parker-Holder , Aldo Pacchiano , Krzysztof Choromanski , Stephen Roberts

Reinforcement learning (RL) is a branch of machine learning which is employed to solve various sequential decision making problems without proper supervision. Due to the recent advancement of deep learning, the newly proposed Deep-RL…

人工智能 · 计算机科学 2019-04-17 Dhruv Ramani

Markov reward processes (MRPs) are used to model stochastic phenomena arising in operations research, control engineering, robotics, and artificial intelligence, as well as communication and transportation networks. In many of these cases,…

机器学习 · 统计学 2020-09-17 Ashwin Pananjady , Martin J. Wainwright

While reinforcement learning (RL) has achieved great success in acquiring complex skills solely from environmental interactions, it assumes that resets to the initial state are readily available at the end of each episode. Such an…

机器学习 · 计算机科学 2023-06-12 Jigang Kim , Daesol Cho , H. Jin Kim

Reliant on too many experiments to learn good actions, current Reinforcement Learning (RL) algorithms have limited applicability in real-world settings, which can be too expensive to allow exploration. We propose an algorithm for batch RL,…

机器学习 · 计算机科学 2021-12-07 Rasool Fakoor , Jonas Mueller , Kavosh Asadi , Pratik Chaudhari , Alexander J. Smola

Inverse reinforcement learning (IRL) aims to learn a reward function and a corresponding policy that best fit the demonstrated trajectories of an expert. However, current IRL works cannot learn incrementally from an ongoing trajectory…

机器学习 · 计算机科学 2025-07-24 Shicheng Liu , Minghui Zhu

Learning physical dynamics in a series of non-stationary environments is a challenging but essential task for model-based reinforcement learning (MBRL) with visual inputs. It requires the agent to consistently adapt to novel tasks without…

机器学习 · 计算机科学 2025-07-08 Minting Pan , Wendong Zhang , Geng Chen , Xiangming Zhu , Siyu Gao , Yunbo Wang , Xiaokang Yang

Many reinforcement learning (RL) environments consist of independent entities that interact sparsely. In such environments, RL agents have only limited influence over other entities in any particular situation. Our idea in this work is that…

机器学习 · 计算机科学 2021-12-03 Maximilian Seitzer , Bernhard Schölkopf , Georg Martius

Most reinforcement learning (RL) methods only focus on learning a single task from scratch and are not able to use prior knowledge to learn other tasks more effectively. Context-based meta RL techniques are recently proposed as a possible…

机器学习 · 计算机科学 2022-08-01 Xu Han , Feng Wu

Residual Reinforcement Learning (RL) is a popular approach for adapting pretrained policies by learning a lightweight residual policy that provides corrective actions. While Residual RL is more sample-efficient than finetuning the entire…

Reinforcement learning (RL) methods learn optimal decisions in the presence of a stationary environment. However, the stationary assumption on the environment is very restrictive. In many real world problems like traffic signal control,…

机器学习 · 计算机科学 2020-06-08 Sindhu Padakandla , Prabuchandran K. J , Shalabh Bhatnagar

Model-based Reinforcement Learning approaches have the promise of being sample efficient. Much of the progress in learning dynamics models in RL has been made by learning models via supervised learning. But traditional model-based…

机器学习 · 计算机科学 2019-06-12 Shagun Sodhani , Anirudh Goyal , Tristan Deleu , Yoshua Bengio , Sergey Levine , Jian Tang

Reinforcement learning (RL) is an appealing paradigm for training intelligent agents, enabling policy acquisition from the agent's own autonomously acquired experience. However, the training process of RL is far from automatic, requiring…

人工智能 · 计算机科学 2025-02-25 Zhao Yang , Thomas M. Moerland , Mike Preuss , Aske Plaat , Edward S. Hu

In this paper, we consider a transfer Reinforcement Learning (RL) problem in continuous state and action spaces, under unobserved contextual information. For example, the context can represent the mental view of the world that an expert…

机器学习 · 计算机科学 2021-06-08 Chenyu Liu , Yan Zhang , Yi Shen , Michael M. Zavlanos

Although reinforcement learning (RL) can provide reliable solutions in many settings, practitioners are often wary of the discrepancies between the RL solution and their status quo procedures. Therefore, they may be reluctant to adapt to…

机器学习 · 计算机科学 2019-06-03 Mohammadreza Nazari , Majid Jahani , Lawrence V. Snyder , Martin Takáč