English
Related papers

Related papers: Reward-Based Environment States for Robot Manipula…

200 papers

Representation learning is a central challenge across a range of machine learning areas. In reinforcement learning, effective and functional representations have the potential to tremendously accelerate learning progress and solve more…

Machine Learning · Computer Science 2019-01-30 Dibya Ghosh , Abhishek Gupta , Sergey Levine

Recent studies show that deep reinforcement learning (DRL) agents tend to overfit to the task on which they were trained and fail to adapt to minor environment changes. To expedite learning when transferring to unseen tasks, we propose a…

Artificial Intelligence · Computer Science 2024-02-22 Guy Azran , Mohamad H. Danesh , Stefano V. Albrecht , Sarah Keren

Robot control problems are often structured with a policy function that maps state values into control values, but in many dynamic problems the observed state can have a difficult to characterize relationship with useful policy actions. In…

Machine Learning · Computer Science 2020-05-01 Max Pflueger , Gaurav S. Sukhatme

Guided Policy Search enables robots to learn control policies for complex manipulation tasks efficiently. Therein, the control policies are represented as high-dimensional neural networks which derive robot actions based on states. However,…

Robotics · Computer Science 2019-02-20 Philipp Ennen , Pia Bresenitz , Rene Vossen , Frank Hees

Imitation learning is an effective alternative approach to learn a policy when the reward function is sparse. In this paper, we consider a challenging setting where an agent and an expert use different actions from each other. We assume…

Machine Learning · Computer Science 2019-08-27 Konrad Zolna , Negar Rostamzadeh , Yoshua Bengio , Sungjin Ahn , Pedro O. Pinheiro

Grasp-based manipulation tasks are fundamental to robots interacting with their environments, yet gripper state ambiguity significantly reduces the robustness of imitation learning policies for these tasks. Data-driven solutions face the…

Robotics · Computer Science 2025-04-01 Yifei Yang , Lu Chen , Zherui Song , Yenan Chen , Wentao Sun , Zhongxiang Zhou , Rong Xiong , Yue Wang

We present a map-less path planning algorithm based on Deep Reinforcement Learning (DRL) for mobile robots navigating in unknown environment that only relies on 40-dimensional raw laser data and odometry information. The planner is trained…

Robotics · Computer Science 2020-02-12 Nicolò Botteghi , Beril Sirmacek , Khaled A. A. Mustafa , Mannes Poel , Stefano Stramigioli

Learning complex manipulation tasks in realistic, obstructed environments is a challenging problem due to hard exploration in the presence of obstacles and high-dimensional visual observations. Prior work tackles the exploration problem by…

Machine Learning · Computer Science 2021-11-12 I-Chun Arthur Liu , Shagun Uppal , Gaurav S. Sukhatme , Joseph J. Lim , Peter Englert , Youngwoon Lee

While the recent advances in deep reinforcement learning have achieved impressive results in learning motor skills, many of the trained policies are only capable within a limited set of initial states. We propose a technique to break down a…

Robotics · Computer Science 2018-11-19 Visak C. V. Kumar , Sehoon Ha , C. Karen Liu

Exploration of indoor environments has recently experienced a significant interest, also thanks to the introduction of deep neural agents built in a hierarchical fashion and trained with Deep Reinforcement Learning (DRL) on simulated…

Generating context-adaptive manipulation and grasping actions is a challenging problem in robotics. Classical planning and control algorithms tend to be inflexible with regard to parameterization by external variables such as object shapes.…

Robotics · Computer Science 2024-11-01 Tim R. Winter , Ashok M. Sundaram , Werner Friedl , Maximo A. Roa , Freek Stulp , João Silvério

We study the problem of learning exploration-exploitation strategies that effectively adapt to dynamic environments, where the task may change over time. While RNN-based policies could in principle represent such strategies, in practice…

Conventional state representations in reinforcement learning often omit critical task-related details, presenting a significant challenge for value networks in establishing accurate mappings from states to task rewards. Traditional methods…

Artificial Intelligence · Computer Science 2024-07-19 Boyuan Wang , Yun Qu , Yuhang Jiang , Jianzhun Shao , Chang Liu , Wenming Yang , Xiangyang Ji

Reinforcement learning has shown strong performance in robotic manipulation, but learned policies often degrade in performance when test conditions differ from the training distribution. This limitation is especially important in…

Robotics · Computer Science 2026-04-02 Shaifalee Saxena , Rafael Fierro , Alexander Scheinker

Many essential manipulation tasks - such as food preparation, surgery, and craftsmanship - remain intractable for autonomous robots. These tasks are characterized not only by contact-rich, force-sensitive dynamics, but also by their…

Robotics · Computer Science 2026-03-04 Toru Lin , Shuying Deng , Zhao-Heng Yin , Pieter Abbeel , Jitendra Malik

We describe an algorithm for motion planning based on expert demonstrations of a skill. In order to teach robots to perform complex object manipulation tasks that can generalize robustly to new environments, we must (1) learn a…

Robotics · Computer Science 2016-02-16 Chris Paxton , Marin Kobilarov , Gregory D. Hager

In this work, we evaluate the effectiveness of representation learning approaches for decision making in visually complex environments. Representation learning is essential for effective reinforcement learning (RL) from high-dimensional…

Machine Learning · Computer Science 2022-04-26 Jun Yamada , Karl Pertsch , Anisha Gunjal , Joseph J. Lim

We propose a novel formulation of robotic pick and place as a deep reinforcement learning (RL) problem. Whereas most deep RL approaches to robotic manipulation frame the problem in terms of low level states and actions, we propose a more…

Robotics · Computer Science 2018-02-26 Marcus Gualtieri , Andreas ten Pas , Robert Platt

Human-robot handovers are characterized by high uncertainty and poor structure of the problem that make them difficult tasks. While machine learning methods have shown promising results, their application to problems with large state…

Robotics · Computer Science 2016-10-18 Francesco Riccio , Roberto Capobianco , Daniele Nardi

In this paper, we propose a method for training control policies for human-robot interactions such as handshakes or hand claps via Deep Reinforcement Learning. The policy controls a humanoid Shadow Dexterous Hand, attached to a robot arm.…

Robotics · Computer Science 2020-01-14 Sammy Christen , Stefan Stevsic , Otmar Hilliges