mlsanityData to 14 Oct 2026

Towards a Sample Efficient Reinforcement Learning Pipeline for Vision Based Robotics

arXiv 2105.09719 ↗First posted 20 May 2021cs.AI cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep Reinforcement learning holds the guarantee of empowering self-ruling robots to master enormous collections of conduct abilities with negligible human mediation. The improvements brought by this technique enables robots to perform difficult tasks such as grabbing or reaching targets. Nevertheless, the training process is still time consuming and tedious especially when learning policies only with RGB camera information. This way of learning is capital to transfer the task from simulation to the real world since the only external source of information for the robot in real life is video. In this paper, we study how to limit the time taken for training a robotic arm with 6 Degrees Of Freedom (DOF) to reach a ball from scratch by assembling a pipeline as efficient as possible. The pipeline is divided into two parts: the first one is to capture the relevant information from the RGB video with a Computer Vision algorithm. The second one studies how to train faster a Deep Reinforcement Learning algorithm in order to make the robotic arm reach the target in front of him. Follow this link to find videos and plots in higher resolution: urlhttps://drive.google.com/drive/folders/1lRlDSoPzdGTcVrxNip10olm-DPdn?usp=sharing

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 31 references that are in the map. First posted on arXiv 20 May 2021.

Builds on

23 of 31 references.

References · 23

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  3. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  4. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  5. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  6. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  7. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  8. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
  9. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
  10. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,380
  11. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 743
  12. 2019RLBench: The Robot Learning Benchmark & Learning Environmentcited by 689
11 more
  1. 2018An Introduction to Deep Reinforcement Learningcited by 206
  2. 2017Receptive Field Block Net for Accurate and Fast Object Detectioncited by 141
  3. 2013Deep Learning for Detecting Robotic Graspscited by 116
  4. 2017Virtual to Real Reinforcement Learning for Autonomous Drivingcited by 80
  5. 2019A Survey of Deep Reinforcement Learning in Video Gamescited by 73
  6. 2017OptLayer - Practical Constrained Optimization for Deep Reinforcement Learning in the Real Worldcited by 70
  7. 2019PyRep: Bringing V-REP to Deep Robot Learningcited by 44
  8. 2017Safe and Nested Subgame Solving for Imperfect-Information Gamescited by 41
  9. 2015Towards Vision-Based Deep Reinforcement Learning for Robotic Motion Controlcited by 33
  10. 2021Model Predictive Actor-Critic: Accelerating Robot Skill Acquisition with Deep Reinforcement Learningcited by 28
  11. 2018Deep Learning based Early Detection and Grading of Diabetic Retinopathy Using Retinal Fundus Imagescited by 6

Built on by

Not cited yet.