Ben Abbatematteo

Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes

Annual Review of Control Robotics and Autonomous Systems · 2024-11-26 · 96 citations

Reinforcement learning (RL), particularly its combination with deep neural networks, referred to as deep RL (DRL), has shown tremendous promise across a wide range of applications, suggesting its potential for enabling the development of sophisticated robotic behaviors. Robotics problems, however, pose fundamental difficulties for the application of RL, stemming from the complexity and cost of interacting with the physical world. This article provides a modern survey of DRL for robotics, with a…

Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes

Proceedings of the AAAI Conference on Artificial Intelligence · 2025-04-11 · 58 citations

Reinforcement learning (RL), particularly its combination with deep neural networks referred to as deep RL (DRL), has shown tremendous promise across a wide range of applications, suggesting its potential for enabling the development of sophisticated robotic behaviors. Robotics problems, however, pose fundamental difficulties for the application of RL, stemming from the complexity and cost of interacting with the physical world. These challenges notwithstanding, recent advances have enabled DRL…

ScrewMimic: Bimanual Imitation from Human Videos with Screw Space Projection

2024-07-15 · 6 citations

Composable Interaction Primitives: A Structured Policy Class for Efficiently Learning Sustained-Contact Manipulation Skills

2024-05-13 · 4 citations

We propose a new policy class, Composable Interaction Primitives (CIPs), specialized for learning sustained-contact manipulation skills like opening a drawer, pulling a lever, turning a wheel, or shifting gears. CIPs have two primary design goals: to minimize what must be learned by exploiting structure present in the world and the robot, and to support sequential composition by construction, so that learned skills can be used by a task-level planner. Using an ablation experiment in four simulat…

Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes

arXiv (Cornell University) · 2024-08-07 · 2 citations

Reinforcement learning (RL), particularly its combination with deep neural networks referred to as deep RL (DRL), has shown tremendous promise across a wide range of applications, suggesting its potential for enabling the development of sophisticated robotic behaviors. Robotics problems, however, pose fundamental difficulties for the application of RL, stemming from the complexity and cost of interacting with the physical world. This article provides a modern survey of DRL for robotics, with a p…