paper-with-me

홈 › Papers

A New Perspective on Transformers in Online Reinforcement Learning for Continuous Control

2025-10-15 · Nikita Kachaev, Daniil Zelezetsky, Egor Cherepanov, Alexey K. Kovelev, Aleksandr I. Panov arxiv

Despite their effectiveness and popularity in offline or model-based reinforcement learning (RL), transformers remain underexplored in online model-free RL due to their sensitivity to training setups and model design decisions such as how to structure the policy and value networks, share components, or handle temporal information. In this paper, we show that transformers can be strong baselines for continuous control in online model-free RL. We investigate key design questions: how to condition inputs, share components between actor and critic, and slice sequential data for training. Our experiments reveal stable architectural and training strategies enabling competitive performance across fully and partially observable tasks, and in both vector- and image-based settings. These findings offer practical guidance for applying transformers in online RL.

📄 PDF Abstract BibTeX arXiv:2510.13367

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningContinuous Control

Similar Papers 제목 키워드 기반

Mental Accounts for Actions: EWA-Inspired Attention in Decision Transformers

2025-09-19 · Zahra Aref, Narayan B. Mandayam arxiv

Transformers have emerged as a compelling architecture for sequential decision-making by modeling trajectories via self-attention. In reinforcement learning (RL), they enable return-conditioned control without relying on…

Reinforcement Learning

The Sample Complexity of Online Reinforcement Learning: A Multi-model Perspective

2025-01-27 · Michael Muehlebach, Zhiyu He, Michael I. Jordan

We study the sample complexity of online reinforcement learning in the general setting of nonlinear dynamical systems with continuous state and action spaces. Our analysis accommodates a large class of dynamical systems …

Knowledge Transfer in Multi-Task Deep Reinforcement Learning for Continuous Control

2020-10-15 · NeurIPS 2020 12 · Zhiyuan Xu, Kun Wu, Zhengping Che, Jian Tang 외

While Deep Reinforcement Learning (DRL) has emerged as a promising approach to many complex tasks, it remains challenging to train a single DRL agent that is capable of undertaking multiple different continuous control t…

continuous-controlContinuous ControlDeep Reinforcement LearningMuJoCo+4

RLOC: Neurobiologically Inspired Hierarchical Reinforcement Learning Algorithm for Continuous Control of Nonlinear Dynamical Systems

2019-03-07 · Ekaterina Abramova, Luke Dickens, Daniel Kuhn, Aldo Faisal

Nonlinear optimal control problems are often solved with numerical methods that require knowledge of system's dynamics which may be difficult to infer, and that carry a large computational cost associated with iterative …

continuous-controlContinuous ControlHierarchical Reinforcement LearningModel-based Reinforcement Learning+3

Safe reinforcement learning control for continuous-time nonlinear systems without a backup controller

2022-09-19 · Soutrik Bandyopadhyay, Shubhendu Bhasin

This paper proposes an on-policy reinforcement learning (RL) control algorithm that solves the optimal regulation problem for a class of uncertain continuous-time nonlinear systems under user-defined state constraints. W…

reinforcement-learningReinforcement Learning (RL)Safe Reinforcement Learning