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

On the reading lists

• #145 in the Top 500 (2026 edition)
• #12 in Reinforcement learning (2026 edition)

Why it matters

Established robust, sample-efficient off-policy continuous control with entropy-regularized actor-critic learning.

Condensed from the expert lists' notes.

The record

First released

2018 (from arXiv 1801.01290)

Citations

12,708 citations, as counted by Papers With Code (CC BY-SA 4.0)

Named by

both expert lists

Also relevant to

Robotics

Score

0.605 · computed rank 145 · consensus 0.76, must-read 0.5, citations percentile 0.935 (2010s · reinforcement-learning), awards 0, existing lists 0. Method