English
Related papers

Related papers: Zero-shot generalization using cascaded system-rep…

200 papers

This study presents a benchmark for evaluating action-constrained reinforcement learning (RL) algorithms. In action-constrained RL, each action taken by the learning system must comply with certain constraints. These constraints are crucial…

Machine Learning · Computer Science 2023-06-30 Kazumi Kasaura , Shuwa Miura , Tadashi Kozuno , Ryo Yonetani , Kenta Hoshino , Yohei Hosoe

We investigate reinforcement learning in the setting of Markov decision processes for a large number of exchangeable agents interacting in a mean field manner. Applications include, for example, the control of a large number of robots…

Optimization and Control · Mathematics 2025-04-30 René Carmona , Mathieu Laurière , Zongjun Tan

Reinforcement learning in massively parallel physics simulations has driven major progress in sim-to-real robot learning. However, current approaches remain brittle and task-specific, relying on extensive per-task engineering to design…

Communication is a critical factor for the big multi-agent world to stay organized and productive. Typically, most previous multi-agent "learning-to-communicate" studies try to predefine the communication protocols or use technologies such…

Artificial Intelligence · Computer Science 2017-10-31 Hangyu Mao , Zhibo Gong , Yan Ni , Zhen Xiao

In the trial-and-error mechanism of reinforcement learning (RL), a notorious contradiction arises when we expect to learn a safe policy: how to learn a safe policy without enough data and prior model about the dangerous region? Existing…

Machine Learning · Computer Science 2021-11-29 Haitong Ma , Changliu Liu , Shengbo Eben Li , Sifa Zheng , Wenchao Sun , Jianyu Chen

The continual learning (CL) paradigm aims to enable neural networks to learn tasks continually in a sequential fashion. The fundamental challenge in this learning paradigm is catastrophic forgetting previously learned tasks when the model…

Machine Learning · Computer Science 2021-04-15 Ghada Sokar , Decebal Constantin Mocanu , Mykola Pechenizkiy

We propose a conceptually simple and lightweight framework for deep reinforcement learning that uses asynchronous gradient descent for optimization of deep neural network controllers. We present asynchronous variants of four standard…

Recently, empowered with the powerful capabilities of neural networks, reinforcement learning (RL) has successfully tackled numerous challenging tasks. However, while these models demonstrate enhanced decision-making abilities, they are…

Machine Learning · Computer Science 2025-10-09 Zhengpeng Xie , Yulong Zhang

In this work, we investigate how spatially grounded auxiliary representations can provide both broad, high-level grounding as well as direct, actionable information to improve policy learning performance and generalization for dexterous…

Robotics · Computer Science 2025-06-09 Jonathan Yang , Chuyuan Kelly Fu , Dhruv Shah , Dorsa Sadigh , Fei Xia , Tingnan Zhang

Neural networks have been shown vulnerable to a variety of adversarial algorithms. A crucial step to understanding the rationale for this lack of robustness is to assess the potential of the neural networks' representation to encode the…

Computer Vision and Pattern Recognition · Computer Science 2020-07-17 Shashank Kotyan , Danilo Vasconcellos Vargas , Moe Matsuki

While sparse coding-based clustering methods have shown to be successful, their bottlenecks in both efficiency and scalability limit the practical usage. In recent years, deep learning has been proved to be a highly effective, efficient and…

Machine Learning · Computer Science 2015-10-19 Zhangyang Wang , Shiyu Chang , Jiayu Zhou , Meng Wang , Thomas S. Huang

Deep Reinforcement Learning (RL) has shown great success in learning complex control policies for a variety of applications in robotics. However, in most such cases, the hardware of the robot has been considered immutable, modeled as part…

Robotics · Computer Science 2020-11-10 Tianjian Chen , Zhanpeng He , Matei Ciocarlie

Studies that broaden drone applications into complex tasks require a stable control framework. Recently, deep reinforcement learning (RL) algorithms have been exploited in many studies for robot control to accomplish complex tasks.…

This paper deals with distributed policy optimization in reinforcement learning, which involves a central controller and a group of learners. In particular, two typical settings encountered in several applications are considered:…

Machine Learning · Computer Science 2021-04-21 Tianyi Chen , Kaiqing Zhang , Georgios B. Giannakis , Tamer Başar

Representation learning based on multi-task pretraining has become a powerful approach in many domains. In particular, task-aware representation learning aims to learn an optimal representation for a specific target task by sampling data…

Machine Learning · Computer Science 2023-06-16 Yifang Chen , Yingbing Huang , Simon S. Du , Kevin Jamieson , Guanya Shi

Nowadays, liquid rocket engines use closed-loop control at most near steady operating conditions. The control of the transient phases is traditionally performed in open-loop due to highly nonlinear system dynamics. This situation is…

Machine Learning · Computer Science 2021-05-27 Günther Waxenegger-Wilfing , Kai Dresia , Jan Christian Deeken , Michael Oschwald

In this paper, we propose a principled deep reinforcement learning (RL) approach that is able to accelerate the convergence rate of general deep neural networks (DNNs). With our approach, a deep RL agent (synonym for optimizer in this work)…

Machine Learning · Computer Science 2017-07-14 Jie Fu

Reinforcement Learning (RL) has witnessed great strides for quadruped locomotion, with continued progress in the reliable sim-to-real transfer of policies. However, it remains a challenge to reuse a policy on another robot, which could save…

Robotics · Computer Science 2022-09-29 He Li , Tingnan Zhang , Wenhao Yu , Patrick M. Wensing

Behavior cloning has shown promise for robot manipulation, but real-world demonstrations are costly to acquire at scale. While simulated data offers a scalable alternative, particularly with advances in automated demonstration generation,…

Robotics · Computer Science 2026-01-19 Shuo Cheng , Liqian Ma , Zhenyang Chen , Ajay Mandlekar , Caelan Garrett , Danfei Xu

This paper introduces a novel neural network-based reinforcement learning approach for robot gaze control. Our approach enables a robot to learn and to adapt its gaze control strategy for human-robot interaction neither with the use of…

Robotics · Computer Science 2019-02-18 Stéphane Lathuilière , Benoit Massé , Pablo Mesejo , Radu Horaud