Status
SteamPeaks
ChartsSalesUpcomingPatchesNewsCalculator
New on SteamEvery app, DLC and depot the minute Steam creates itAppsEvery app on Steam, newest change firstPackagesSubs and bundles, and what each containsDepotsDepots, manifests and install sizesTagsSteam's user tags and the games under themDevelopers & publishersCompanies and their cataloguesTechnologiesEngines, SDKs and anti-cheat found in the filesChange historyEvery PICS changelist as it lands
SignalsNineteen readings of the whole catalogueCompareAny games side by sideRecordsAll-time peaks and the days they were setReportsWeekly and monthly write-upsAlerts & newsroomWatch a game, get told when it movesSteam statusIs Steam up, right nowWeb API explorerTry the endpoints in the browser
NewsSteam's own announcements and the sales calendarCalculatorWhat a Steam account is worth, and its pile of shame
/
Sign in
/
SteamPeaks
The ultimate resource for Steam data.
ExploreChartsSalesSales and festsUpcomingPatchesNewsRecordsTrendingSignals
DatabaseAppsPackagesDepotsTagsDevelopersTechnologiesChange history
ToolsCalculatorCompareSearchAlertsSteam statusAPI
SiteMethodologyFAQDiscordSupportSign in via Steam
Not affiliated with Valve or Steam. Game names and artwork belong to their owners. All times UTC.
PrivacyCookiesFair useStatus
sfsimNewsReinforcement Learning of Rocket Launch
In-game event

Reinforcement Learning of Rocket Launch

sfsim · published 28 May 2026, 22:35 UTC

All newsPlayers around this dateRead on Steam

Hi,

I have released version 0.19-1 of sfsim.

This version introduces scaling of the graphical user interface. All the user interface elements are scaled up when switching to fullscreen or back taking into account the monitor resolution. This should make it easier to start implementing multi function displays (MFDs).

Furthermore I am working on launch trajectory optimization. It is not optimal yet as the rocket should first go up to leave the atmosphere more quickly. I am using proximal policy optimization (PPO) which is a reinforcement learning method which has become popular. Hopefully PPO will be able to also solve the more difficult problem of reentry. If you want to know more about this reinforcement learning method, I posted an article about PPO at ClojureCivitas.

Let me know any feedback and comments in the sfsim playtest discussion forum.

Enjoy!

More from sfsim

Other announcements

All news
Community6 Sep 2026ShockwavesI am excited to share early results of shockwave rendering with the community! I would like to add visualization of a glowing shockwave during atmospheric reentry in the sfsim spaceflight simulator. I explored possible approaches by discussing the problem with Google Gemini. Popular approaches seem to use meshes with animated semi-transparent noise textures. However this still leaves the proble…Major update27 Aug 2026Deferred RenderingI have released version 0.30-1 of sfsim . This release introduces a major overhaul of the rendering code as well as a runway for the spacecraft. The rendering system is implemented using the Clojure programming language as well as GLSL . LWJGL3 is used to access the graphics card’s OpenGL bindings. The new rendering code uses deferred shading , which first computes and stores per-pixel geometry…Game update7 Aug 2026Metallic and roughness factorI have released version 0.29-1 of sfsim . The Open Asset Import Library (assimp) which is shipped with the LWJGL3 library has been updated some time ago. I am now able to access the metallic value and the roughness value from the glTF exported by Blender . The metallic and roughness value are now used in the model shader programs so that the spacecraft has a more metallic surface. In the meanti…