Methods › Reinforcement Learning › Exploration Strategies › gSDE
Generalized State-Dependent Exploration
gSDE
Introduced by Antonin Raffin et al. in Smooth Exploration for Robotic Reinforcement Learning
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Generalized State-Dependent Exploration, or gSDE, is an exploration method for reinforcement learning that uses more general features and re-sampling the noise periodically.
State-Dependent Exploration (SDE) is an intermediate solution for exploration that consists in adding noise as a function of the state sₜ, to the deterministic action μ(sₜ). At the beginning of an episode, the parameters θ_ϵ of that exploration function are drawn from a Gaussian distribution. The resulting action aₜ is as follows:
aₜ=μ(sₜ ; θ_μ)+ϵ(sₜ ; θ_ϵ), θ_ϵ ∼𝒩(0, σ²)
This episode-based exploration is smoother and more consistent than the unstructured step-based exploration. Thus, during one episode, instead of oscillating around a mean value, the action a for a given state s will be the same.
In the case of a linear exploration function ϵ(s ; θ_ϵ)=θ_ϵ s, by operation on Gaussian distributions, Rückstieß et al. show that the action element aⱼ is normally distributed:
π]ⱼ(aⱼ |s) ∼𝒩(μⱼ(s), σ̂ⱼ̂²)
where σ̂ is a diagonal matrix with elements σ̂ⱼ=√(∑ᵢ(σ_(i j) sᵢ)²).
Because we know the policy distribution, we can obtain the derivative of the log-likelihood logπ(a |s) with respect to the variance σ :
(∂logπ(a |s))/(∂σ_(i j))=((aⱼ-μⱼ)²-σ̂ⱼ̂²)/σ̂ⱼ³ (sᵢ² σ_(i j))/σ̂ⱼ̂
This can be easily plugged into the likelihood ratio gradient estimator, which allows to adapt σ during training. SDE is therefore compatible with standard policy gradient methods, while addressing most shortcomings of the unstructured exploration.
For gSDE, two improvements are suggested:
- We sample the parameters θ_ϵ of the exploration function every n steps instead of every episode.
- Instead of the state s, we can in fact use any features. We chose policy features z_μ(s ; θ_(z_μ)) (last layer before the deterministic output .μ(s)=θ_μ z_μ(s ; θ_(z_μ))) as input to the noise function ϵ(s ; θ_ϵ)=θ_ϵ z_μ(s)
In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.
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.
Papers archive 2025-07-28
archive papers tagged: 1 · with a code link: 1 · where Syntology ran a sample: 1 (1 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 (1 of 1 tagged: 1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: paper 1 of 1, 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.
-
Smooth Exploration for Robotic Reinforcement Learning 12 May 2020 · 4 repositories · arXiv:2005.05719Syntology community repositories only · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
Tasks archive 2025-07-28
5 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Continuous Control | 1 |
| Reinforcement Learning | 1 |
| Reinforcement Learning (RL) | 1 |
| continuous-control | 1 |
| reinforcement-learning | 1 |
Usage over time archive 2025-07-28
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
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