Reinforcement learning in robotics: A survey

Jens Kober; J. Andrew Bagnell; Jan Peters

doi:https://doi.org/10.1177/0278364913495721

Reinforcement learning in robotics: A survey

2013 · The International Journal of Robotics Research · 3,154 citations · 7 from inside this corpus

Jens Kober, J. Andrew Bagnell, Jan Peters

Reinforcement learning offers to robotics a framework and set of tools for the design of sophisticated and hard-to-engineer behaviors. Conversely, the challenges of robotic problems provide both inspiration, impact, and validation for developments in reinforcement learning. The relationship between disciplines has sufficient promise to be likened to that between physics and mathematics. In this article, we attempt to strengthen the links between the two research communities by providing a survey of work in reinforcement learning for behavior generation in robots. We highlight both key challenges in robot reinforcement learning as well as notable successes. We discuss how contributions tamed the complexity of the domain and study the role of algorithms, representations, and prior knowledge in achieving these successes. As a result, a particular focus of our paper lies on the choice between model-based and model-free as well as between value-function-based and policy-search methods. By analyzing a simple problem in some detail we demonstrate how reinforcement learning approaches may be profitably applied, and we note throughout open questions and the tremendous potential for future research.

26 of 26 neighbouring works in this corpus. Blue is what this paper cites; orange is what cites it, and a dashed line is one neighbour citing another. Only the largest labels are drawn — every node carries its full title on hover.

this paper works it cites works citing it node size = global citations · hover for the full title

Citation edge evidence

Each row is directed from the citing work to the cited work. Source status remains readable without the interactive graph.

Mastering the game of Go without human knowledge→Reinforcement learning in robotics: A surveyLegacy edge — source detail unavailable
How artificial intelligence will change the future of marketing→Reinforcement learning in robotics: A surveyLegacy edge — source detail unavailable
End-to-end training of deep visuomotor policies→Reinforcement learning in robotics: A surveyLegacy edge — source detail unavailable
A State-of-the-Art Survey on Deep Learning Theory and Architectures→Reinforcement learning in robotics: A surveyLegacy edge — source detail unavailable
Target-driven visual navigation in indoor scenes using deep reinforcement learning→Reinforcement learning in robotics: A surveyLegacy edge — source detail unavailable
Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates→Reinforcement learning in robotics: A surveyLegacy edge — source detail unavailable
End-to-End Training of Deep Visuomotor Policies→Reinforcement learning in robotics: A surveyLegacy edge — source detail unavailable
Reinforcement learning in robotics: A survey→Genetic AlgorithmsLegacy edge — source detail unavailable
Reinforcement learning in robotics: A survey→Gaussian Processes for Machine LearningLegacy edge — source detail unavailable
Reinforcement learning in robotics: A survey→Reinforcement Learning: A SurveyLegacy edge — source detail unavailable
Reinforcement learning in robotics: A survey→Markov Decision Processes: Discrete Stochastic Dynamic Programming.Legacy edge — source detail unavailable
Reinforcement learning in robotics: A survey→Pattern Recognition and Machine Learning (Information Science and Statistics)Legacy edge — source detail unavailable
Reinforcement learning in robotics: A survey→Simple statistical gradient-following algorithms for connectionist reinforcement learningLegacy edge — source detail unavailable
Reinforcement learning in robotics: A survey→Introduction to Reinforcement LearningLegacy edge — source detail unavailable
Reinforcement learning in robotics: A survey→Markov Decision ProcessesLegacy edge — source detail unavailable
Reinforcement learning in robotics: A survey→Policy Gradient Methods for Reinforcement Learning with Function ApproximationLegacy edge — source detail unavailable
Reinforcement learning in robotics: A survey→A survey of robot learning from demonstrationLegacy edge — source detail unavailable
Reinforcement learning in robotics: A survey→Apprenticeship learning via inverse reinforcement learningLegacy edge — source detail unavailable
Reinforcement learning in robotics: A survey→International Conference on Machine Learning (ICML)-2005Legacy edge — source detail unavailable
Reinforcement learning in robotics: A survey→Advances in Neural Information Processing Systems 27 (NIPS 2014)Legacy edge — source detail unavailable
Reinforcement learning in robotics: A survey→Maximum Entropy Inverse Reinforcement LearningLegacy edge — source detail unavailable
Reinforcement learning in robotics: A survey→Introduction to Stochastic Search and OptimizationLegacy edge — source detail unavailable
Reinforcement learning in robotics: A survey→Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning)Legacy edge — source detail unavailable
Reinforcement learning in robotics: A survey→Advances in Neural Information Processing Systems 19 (NIPS 2006)Legacy edge — source detail unavailable
Reinforcement learning in robotics: A survey→Adaptive Computation and Machine LearningLegacy edge — source detail unavailable
Reinforcement learning in robotics: A survey→Integrated Architectures for Learning, Planning, and Reacting Based on Approximating Dyna…Legacy edge — source detail unavailable
A survey of robot learning from demonstration→Apprenticeship learning via inverse reinforcement learningLegacy edge — source detail unavailable
A survey of robot learning from demonstration→Maximum Entropy Inverse Reinforcement LearningLegacy edge — source detail unavailable
Maximum Entropy Inverse Reinforcement Learning→Apprenticeship learning via inverse reinforcement learningLegacy edge — source detail unavailable
Reinforcement Learning: A Survey→Integrated Architectures for Learning, Planning, and Reacting Based on Approximating Dyna…Legacy edge — source detail unavailable
Reinforcement Learning: A Survey→Markov Decision Processes: Discrete Stochastic Dynamic Programming.Legacy edge — source detail unavailable
Reinforcement Learning: A Survey→Simple statistical gradient-following algorithms for connectionist reinforcement learningLegacy edge — source detail unavailable
End-to-End Training of Deep Visuomotor Policies→Simple statistical gradient-following algorithms for connectionist reinforcement learningLegacy edge — source detail unavailable
End-to-End Training of Deep Visuomotor Policies→End-to-end training of deep visuomotor policiesLegacy edge — source detail unavailable
Policy Gradient Methods for Reinforcement Learning with Function Approximation→Introduction to Reinforcement LearningLegacy edge — source detail unavailable
Policy Gradient Methods for Reinforcement Learning with Function Approximation→Simple statistical gradient-following algorithms for connectionist reinforcement learningLegacy edge — source detail unavailable
Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates→Simple statistical gradient-following algorithms for connectionist reinforcement learningLegacy edge — source detail unavailable
Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates→End-to-End Training of Deep Visuomotor PoliciesLegacy edge — source detail unavailable
Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates→Policy Gradient Methods for Reinforcement Learning with Function ApproximationLegacy edge — source detail unavailable
Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates→End-to-end training of deep visuomotor policiesLegacy edge — source detail unavailable
A State-of-the-Art Survey on Deep Learning Theory and Architectures→End-to-End Training of Deep Visuomotor PoliciesLegacy edge — source detail unavailable
A State-of-the-Art Survey on Deep Learning Theory and Architectures→Mastering the game of Go without human knowledgeLegacy edge — source detail unavailable
A State-of-the-Art Survey on Deep Learning Theory and Architectures→End-to-end training of deep visuomotor policiesLegacy edge — source detail unavailable
Target-driven visual navigation in indoor scenes using deep reinforcement learning→End-to-End Training of Deep Visuomotor PoliciesLegacy edge — source detail unavailable
Target-driven visual navigation in indoor scenes using deep reinforcement learning→End-to-end training of deep visuomotor policiesLegacy edge — source detail unavailable
End-to-end training of deep visuomotor policies→Simple statistical gradient-following algorithms for connectionist reinforcement learningLegacy edge — source detail unavailable
Adaptive Computation and Machine Learning→Reinforcement Learning: A SurveyLegacy edge — source detail unavailable

What this paper cites, inside the corpus

Paper	Year	Cited
Genetic Algorithms	2002	16,154
Gaussian Processes for Machine Learning	2005	10,470
Reinforcement Learning: A Survey	1996	8,953
Markov Decision Processes: Discrete Stochastic Dynamic Programming.	1995	8,450
Pattern Recognition and Machine Learning (Information Science and Statistics)	2006	8,359
Simple statistical gradient-following algorithms for connectionist reinforcement learning	1992	7,519
Introduction to Reinforcement Learning	1998	6,917
Markov Decision Processes	1994	6,019
Policy Gradient Methods for Reinforcement Learning with Function Approximation	1999	4,966
A survey of robot learning from demonstration	2008	3,289
Apprenticeship learning via inverse reinforcement learning	2004	2,895
International Conference on Machine Learning (ICML)-2005	2006	2,486
Advances in Neural Information Processing Systems 27 (NIPS 2014)	2014	2,396
Maximum Entropy Inverse Reinforcement Learning	2018	2,055
Introduction to Stochastic Search and Optimization	2003	1,911
Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning)	2005	1,859
Advances in Neural Information Processing Systems 19 (NIPS 2006)	2006	1,607
Adaptive Computation and Machine Learning	2012	1,437
Integrated Architectures for Learning, Planning, and Reacting Based on Approximating Dyna…	1990	1,375

What cites it, inside the corpus

Paper	Year	Cited
Mastering the game of Go without human knowledge	2017	9,313
How artificial intelligence will change the future of marketing	2019	2,670
End-to-end training of deep visuomotor policies	2016	1,706
A State-of-the-Art Survey on Deep Learning Theory and Architectures	2019	1,619
Target-driven visual navigation in indoor scenes using deep reinforcement learning	2017	1,520
Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates	2017	1,468
End-to-End Training of Deep Visuomotor Policies	2015	1,400

Links

Download BibTeX · Download RIS · DOI · Open access copy · OpenAlex record

Topics

Reinforcement Learning in Robotics	Computer Science
Evolutionary Algorithms and Applications	Computer Science
Advanced Multi-Objective Optimization Algorithms	Computer Science

Is this record sound?

complete

Nothing in this record contradicts itself and no field we check is missing.

supports3 author record(s) attached.
supports262 reference(s) recorded.
neutralThe DOI carries no year to check against.
supportsA title is present.

Provenance

Everything above was read from one stored OpenAlex payload, fetched 2026-09-04T03:58:47+00:00.

sha256 a08467ae9504f237…