Methods › Reinforcement Learning › Policy Gradient Methods › Soft Actor-Critic (Autotuned Temperature)

Soft Actor-Critic (Autotuned Temperature)

6 papers tagged archive 2025-07-28

Introduced by Tuomas Haarnoja et al. in Soft Actor-Critic Algorithms and Applications

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Soft Actor Critic (Autotuned Temperature is a modification of the SAC reinforcement learning algorithm. SAC can suffer from brittleness to the temperature hyperparameter. Unlike in conventional reinforcement learning, where the optimal policy is independent of scaling of the reward function, in maximum entropy reinforcement learning the scaling factor has to be compensated by the choice a of suitable temperature, and a sub-optimal temperature can drastically degrade performance. To resolve this issue, SAC with Autotuned Temperature has an automatic gradient-based temperature tuning method that adjusts the expected entropy over the visited states to match a target value.

PaperSource

In Syntology for a different name, 'soft actor-critic', about another paper, arXiv:1801.01290: repository known, no verified implementation (declared_code; repositories: 5 listed of 86 in the graph, strongest link: official). The lookup matched a different name in Syntology's graph, 'soft actor-critic' (resolution: token_match); this answer is about that name. About another paper: this answer is about arXiv:1801.01290, while the archive credits arXiv:1812.05905.

Code Syntology holds under other names, as the lookup lists them (code_nearby); not a complete list, and none of them is this method.

Origin paper of this answer, arXiv:1801.01290 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 91 ran (of which 61 constructed an object rather than computing a result; 73 with no instrument failure: 3 honoured, 1 violated, 69 with no contract checked; 18 where Syntology's instrument failed) · 57 unverified (of 148 harvested samples) · 66 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).

Papers archive 2025-07-28

archive papers tagged: 6 · with a code link: 6 · where Syntology ran a sample: 4 (4 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (4 of 6 tagged: 4 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 6 of 6, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

Tasks archive 2025-07-28

9 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Reinforcement Learning (RL)4
Reinforcement Learning3
reinforcement-learning3
Continuous Control1
Control with Prametrised Actions1
Decision Making1
Deep Reinforcement Learning1
Offline RL1
continuous-control1

Usage over time archive 2025-07-28

Papers per year tagged with Soft Actor-Critic (Autotuned Temperature): 2018 to 2022, peak 2 2 0 2018: 1 paper 2018 2019: 1 paper 2019 2020: 2 papers 2020 2021: 0 papers 2021 2022: 2 papers 2022
Papers per year the archive tags with this method, by the paper's archive date (6 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Policy Gradient Methods

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections