Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor

Tuomas Haarnoja; Aurick Zhou; Pieter Abbeel; Sergey Levine

doi:https://doi.org/10.48550/arxiv.1801.01290

Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor

2018 · arXiv (Cornell University) · 3,500 citations · 1 from inside this corpus

Tuomas Haarnoja, Aurick Zhou, Pieter Abbeel, Sergey Levine

The source holds an abstract for this work, but its best open-access copy is under no open licence, which does not permit us to republish the text. Read it at the source below.

12 of 12 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.

Addressing Function Approximation Error in Actor-Critic Methods→Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochast…Legacy edge — source detail unavailable
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochast…→[No title in the source record — DROPS (Schloss Dagstuhl – Leibniz Center for Informatics…Legacy edge — source detail unavailable
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochast…→Mastering the game of Go with deep neural networks and tree searchLegacy edge — source detail unavailable
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochast…→Diagnosing Non-Intermittent Anomalies in Reinforcement Learning Policy Executions (Short …Legacy edge — source detail unavailable
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochast…→Simple statistical gradient-following algorithms for connectionist reinforcement learningLegacy edge — source detail unavailable
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochast…→Continuous control with deep reinforcement learningLegacy edge — source detail unavailable
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochast…→Playing Atari with Deep Reinforcement LearningLegacy edge — source detail unavailable
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochast…→Maximum Entropy Inverse Reinforcement LearningLegacy edge — source detail unavailable
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochast…→Deterministic Policy Gradient AlgorithmsLegacy edge — source detail unavailable
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochast…→End-to-end training of deep visuomotor policiesLegacy edge — source detail unavailable
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochast…→Deep Reinforcement Learning That MattersLegacy edge — source detail unavailable
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochast…→Deep reinforcement learning for robotic manipulation with asynchronous off-policy updatesLegacy edge — source detail unavailable
Deterministic Policy Gradient Algorithms→Simple statistical gradient-following algorithms for connectionist reinforcement learningLegacy edge — source detail unavailable
Continuous control with deep reinforcement learning→Playing Atari with Deep Reinforcement LearningLegacy edge — source detail unavailable
Continuous control with deep reinforcement learning→Deterministic Policy Gradient AlgorithmsLegacy edge — source detail unavailable
Mastering the game of Go with deep neural networks and tree search→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→[No title in the source record — DROPS (Schloss Dagstuhl – Leibniz Center for Informatics…Legacy 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 That Matters→Playing Atari with Deep Reinforcement LearningLegacy edge — source detail unavailable
Deep Reinforcement Learning That Matters→Continuous control with deep reinforcement learningLegacy edge — source detail unavailable
Deep Reinforcement Learning That Matters→Mastering the game of Go with deep neural networks and tree searchLegacy edge — source detail unavailable
Deep Reinforcement Learning That Matters→Diagnosing Non-Intermittent Anomalies in Reinforcement Learning Policy Executions (Short …Legacy edge — source detail unavailable
Addressing Function Approximation Error in Actor-Critic Methods→Deterministic Policy Gradient AlgorithmsLegacy edge — source detail unavailable
Addressing Function Approximation Error in Actor-Critic Methods→Continuous control with deep reinforcement learningLegacy edge — source detail unavailable
Addressing Function Approximation Error in Actor-Critic Methods→Diagnosing Non-Intermittent Anomalies in Reinforcement Learning Policy Executions (Short …Legacy edge — source detail unavailable
Addressing Function Approximation Error in Actor-Critic Methods→Deep Reinforcement Learning That MattersLegacy edge — source detail unavailable
Addressing Function Approximation Error in Actor-Critic Methods→[No title in the source record — DROPS (Schloss Dagstuhl – Leibniz Center for Informatics…Legacy edge — source detail unavailable
End-to-end training of deep visuomotor policies→Playing Atari with Deep 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→Continuous control with deep reinforcement learningLegacy edge — source detail unavailable

What this paper cites, inside the corpus

Paper	Year	Cited
[No title in the source record — DROPS (Schloss Dagstuhl – Leibniz Center for Informatics…	2015	50,396
Mastering the game of Go with deep neural networks and tree search	2016	16,014
Diagnosing Non-Intermittent Anomalies in Reinforcement Learning Policy Executions (Short …	2017	11,354
Simple statistical gradient-following algorithms for connectionist reinforcement learning	1992	7,519
Continuous control with deep reinforcement learning	2015	5,370
Playing Atari with Deep Reinforcement Learning	2013	5,104
Maximum Entropy Inverse Reinforcement Learning	2018	2,055
Deterministic Policy Gradient Algorithms	2014	1,736
End-to-end training of deep visuomotor policies	2016	1,706
Deep Reinforcement Learning That Matters	2018	1,580
Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates	2017	1,468

What cites it, inside the corpus

Paper	Year	Cited
Addressing Function Approximation Error in Actor-Critic Methods	2018	2,372

Links

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

Topics

Reinforcement Learning in Robotics	Computer Science
Neural dynamics and brain function	Neuroscience
Advanced Memory and Neural Computing	Engineering

Is this record sound?

complete

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

supports4 author record(s) attached.
supports34 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…