Learning and reusing primitive behaviours to improve Hindsight
Experience Replay sample efficiency

v1v2 (latest)

Learning and reusing primitive behaviours to improve Hindsight Experience Replay sample efficiency

3 October 2023

Francisco Roldan Sanchez

David Córdova Bulens

Kevin McGuinness

Stephen J. Redmond

Noel E. O'Connor

ArXiv (abs)PDF HTML Github

Papers citing "Learning and reusing primitive behaviours to improve Hindsight Experience Replay sample efficiency"

10 / 10 papers shown

Title
Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks Soroush Nasiriany Huihan Liu Yuke Zhu 132 112 0 07 Oct 2021
Conservative Data Sharing for Multi-Task Offline Reinforcement Learning Tianhe Yu Aviral Kumar Yevgen Chebotar Karol Hausman Sergey Levine Chelsea Finn OffRL 82 77 0 16 Sep 2021
Offline Reinforcement Learning as One Big Sequence Modeling Problem Michael Janner Qiyang Li Sergey Levine OffRL 158 685 0 03 Jun 2021
Complex Robotic Manipulation via Graph-Based Hindsight Goal Generation Zhenshan Bing Matthias Brucker F. O. Morin Kai-Qi Huang Alois C. Knoll 55 27 0 27 Jul 2020
SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning Kimin Lee Michael Laskin A. Srinivas Pieter Abbeel OffRL 74 203 0 09 Jul 2020
Experience Replay Optimization Daochen Zha Kwei-Herng Lai Kaixiong Zhou Helen Zhou OffRL 47 103 0 19 Jun 2019
Exploration via Hindsight Goal Generation Zhizhou Ren Kefan Dong Yuanshuo Zhou Qiang Liu Jian-wei Peng 70 90 0 10 Jun 2019
Hindsight Experience Replay Marcin Andrychowicz Dwight Crow Alex Ray Jonas Schneider Rachel Fong Peter Welinder Bob McGrew Joshua Tobin Pieter Abbeel Wojciech Zaremba OffRL 280 2,339 0 05 Jul 2017
Prioritized Experience Replay Tom Schaul John Quan Ioannis Antonoglou David Silver OffRL 231 3,797 0 18 Nov 2015
Continuous control with deep reinforcement learning Timothy Lillicrap Jonathan J. Hunt Alexander Pritzel N. Heess Tom Erez Yuval Tassa David Silver Daan Wierstra 327 13,289 0 09 Sep 2015