Get started
Keyword

off-policy learning

Description: A reinforcement learning approach that learns or evaluates a target policy using experience generated by a different behavior policy.
OpenAlex ID: keywords/off-policy-learning
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
2018 · Haarnoja, Tuomas, Zhou, Aurick, et al. · arXiv (Cornell University) · 5,593
PDF
Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates
2017 · Shixiang Gu, Ethan Holly, et al. · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · 1,485
PDF
Hindsight Experience Replay
2017 · Andrychowicz, Marcin, Wolski, Filip, et al. · arXiv (Cornell University) · 1,317
PDF
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
2018 · Rashid, Tabish, Samvelyan, Mikayel, et al. · arXiv (Cornell University) · 1,019
PDF
Optimal and Autonomous Control Using Reinforcement Learning: A Survey
2017 · Bahare Kiumarsi, Kyriakos G. Vamvoudakis, et al. · IEEE Transactions on Neural Networks and Learning Systems · 895
Double Q-learning
2010 · Hado van Hasselt · Centrum Wiskunde & Informatica (CWI), the national research institute for mathematics and computer science in the Netherlands · 828
PDF
Q-Learning Algorithms: A Comprehensive Classification and Applications
2019 · Beakcheol Jang, Myeonghwi Kim, et al. · IEEE Access · 638
$ {H}_{ {\infty }}$ Tracking Control of Completely Unknown Continuous-Time Systems via Off-Policy Reinforcement Learning
2015 · Hamidreza Modares, Frank L. Lewis, et al. · IEEE Transactions on Neural Networks and Learning Systems · 569
Fast gradient-descent methods for temporal-difference learning with linear function approximation
2009 · Richard S. Sutton, Hamid Reza Maei, et al. · International Conference on Machine Learning · 500
Data-Efficient Hierarchical Reinforcement Learning
2018 · Nachum, Ofir, Gu, Shixiang, et al. · arXiv (Cornell University) · 446
PDF
Eligibility Traces for Off-Policy Policy Evaluation
2000 · Doina Precup, Richard S. Sutton, et al. · ScholarWorks@UMassAmherst (University of Massachusetts Amherst) · 439
PDF
Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction
2019 · Kumar, Aviral, Fu, Justin, et al. · arXiv (Cornell University) · 416
PDF
Doubly Robust Policy Evaluation and Learning
2011 · Dudik, Miroslav, Langford, John, et al. · arXiv (Cornell University) · 383
PDF
Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables
2019 · Rakelly, Kate, Zhou, Aurick, et al. · arXiv (Cornell University) · 371
PDF
Off-Policy Reinforcement Learning for $ H_\infty $ Control Design
2014 · Biao Luo, Huai-Ning Wu, et al. · IEEE Transactions on Cybernetics · 362
PDF
Linearly-solvable Markov decision problems
2007 · Emanuel Todorov · The MIT Press eBooks · 349
H ∞ control of linear discrete-time systems: Off-policy reinforcement learning
2017 · Bahare Kiumarsi, Frank L. Lewis, et al. · Automatica · 338
Visual Reinforcement Learning with Imagined Goals
2018 · Nair, Ashvin, Pong, Vitchyr, et al. · arXiv (Cornell University) · 333
PDF
Model-Free Optimal Tracking Control via Critic-Only Q-Learning
2016 · Biao Luo, Derong Liu, et al. · IEEE Transactions on Neural Networks and Learning Systems · 332
Distributed Distributional Deterministic Policy Gradients
2018 · Barth-Maron, Gabriel, Hoffman, Matthew W., et al. · arXiv (Cornell University) · 329
PDF
Distributional Soft Actor-Critic: Off-Policy Reinforcement Learning for Addressing Value Estimation Errors
2021 · Jingliang Duan, Yang Guan, et al. · IEEE Transactions on Neural Networks and Learning Systems · 326
PDF
Safe and Efficient Off-Policy Reinforcement Learning
2016 · Munos, Rémi, Stepleton, Tom, et al. · arXiv (Cornell University) · 321
PDF
Horde: a scalable real-time architecture for learning knowledge from unsupervised sensorimotor interaction
2011 · Richard S. Sutton, Joseph Modayil, et al. · 301
Learning by Playing - Solving Sparse Reward Tasks from Scratch
2018 · Riedmiller, Martin, Hafner, Roland, et al. · arXiv (Cornell University) · 291
PDF
Safe Exploration in Continuous Action Spaces
2018 · Dalal, Gal, Dvijotham, Krishnamurthy, et al. · arXiv (Cornell University) · 283
PDF
Works count: 2,077
Citation count: 44,990
Year
Topic
Type