Close Menu

    Subscribe to Updates

    Get the latest creative news from FooBar about art, design and business.

    What's Hot

    The Odyssey becomes highest-grossing R-rated film of all time with a $1.35 billion haul, beats Deadpool & Wolverine

    August 21, 2026

    ‘The Odyssey’ becomes highest-grossing R-rated film of all time, beating ‘Deadpool & Wolverine’

    August 21, 2026

    5 TV Shows That Adapted The Story Of The Odyssey

    August 21, 2026
    Facebook X (Twitter) Instagram
    Facebook X (Twitter) Instagram YouTube TikTok
    Comic Vibe
    Friday, August 21
    • Home
    • Comics
      • Comic Vibe News
    • Gaming
    • Movies
    • TV
    • Anime
    • Toys & Collectibles
    • Cosplay
    • Tech
    • Digital Culture
      • Creators & Fan Culture
      • Creator Economy & Fan-Driven Platforms
      • Digital Fandom & Online Communities
      • Metaverse & Virtual Worlds
      • NFTs & Digital Collectibles
      • Virtual Events & Online Conventions
      • Virtual Identity & Avatars
    • Shop
    Comic Vibe
    • Home
    • Contact Us
    • Terms & Conditions
    • Advertise With Us
    • DMCA Policy
    • Privacy Policy
    • About Us
    Home»Gaming»Temporal Augmentations for Streamed Video Games: Supplementary Material
    Gaming

    Temporal Augmentations for Streamed Video Games: Supplementary Material

    JamesBy JamesJuly 11, 2026No Comments6 Mins Read
    Facebook Twitter
    Temporal Augmentations for Streamed Video Games: Supplementary Material
    Share
    Facebook Twitter

    This supplementary website accompanies the paper “Augmentations for Robust and Efficient Imitation Learning in Streamed Video Games,” published at the Conference on Games 2026. The paper studies whether spatiotemporal augmentations that mimic common streaming artifacts like pixelation, blur, scrubs, and ghosting, can improve the sample efficiency and robustness of imitation learning agents trained from limited gameplay demonstrations. On this website, we provide representative examples of the proposed augmentations, qualitative rollout videos of trained agents, and additional visualizations supporting the results reported in the paper. These materials are intended to complement the quantitative evaluations by illustrating both the streaming artifacts modeled by our method and their impact on agent behavior under normal and degraded streaming conditions.

    Compare representative rollouts across Clean, Synthetic, and Real Streaming Noise settings for Game 1: Task 1, Game 1: Task 2, and Game 2: Task 3, organized by demonstration budget and method

    Get the code
    Read the paper

    Representative rollouts

    Best episodes are the highest-scoring latest completed rollouts for a setting. Median episodes are selected from the middle of the score distribution for each setting

    • Clean conditions 

      Evaluation through streaming with no induced lag or introduced visual artifacts

    • Synthetic conditions 

      Evaluation through streaming with no induced lag, using streaming augmentations to introduce visual artifacts

    • Real Streaming Noise conditions 

      Evaluation through streaming with induced lag, leading to visual artifacts that the streaming augmentations are modeled after

    Clean conditions

    Representative median and best rollouts are shown for each available method in this setting

    • Game 1, Task 1 | 12 Milestones

      No augmentation | Avg. 76.7% (9.20 / 12 milestones) | 5 seeds

      Median episode: 66.7%
      Best episode: 100%

      All augmentation | Avg: 85.8% (10.30 / 12 milestones) | 5 seeds

      Median episode: 100%
      Best episode: 100%

      Game 1, Task 2 | 11 Milestones

      No augmentation | Avg: 94.4% (10.38 / 11 milestones) | 5 seeds

      Median episode: 100%
      Best episode: 100%

      All augmentation | Avg: 97.5% (10.72 / 11 milestones) | 5 seeds

      Median episode: 100%
      Best episode: 100%

      Game 2, Task 3 | 15 Milestones

      No augmentation | Avg: 55.2% (8.28 / 15) | 5 seeds

      Median episode: 60%
      Best episode: 100%

      All augmentation | Avg: 65.1% (9.76 / 15 milestones) | 5 seeds

      Median episode: 66.7%
      Best episode: 100%
    • Game 1, Task 1 | 12 Milestones

      No augmentation | Avg: 43.3% (5.20 / 12 milestones) | 5 seeds

      Median episode: 50.0%
      Best episode: 50.0%

      All augmentation | Avg: 84.7% (10.16 / 12 milestones) | 5 seeds

      Median episode: 91.7%
      Best episode: 100%

      Game 1, Task 2 | 11 Milestones

      No augmentation | Avg: 88.7% (9.76 / 11 milestones) | 5 seeds

      Median episode: 90.9%
      Best episode: 100%

      All augmentation | Avg: 98% (10.78 / 11 milestones) | 5 seeds

      Median episode: 100%
      Best episode: 100%
    • Game 1, Task 1 | 12 Milestones

      No augmentation | Avg: 44% (5.28 / 12 milestones) | 5 seeds

      Median episode: 41.7%
      Best episode: 66.7%

      All augmentation | Avg: 79.2% (9.50 / 12 milestones) | 5 seeds

      Median episode: 91.7%
      Best episode: 100%

      Game 1, Task 2 | 11 Milestones

      No augmentation | Avg: 88% (9.68 / 11 milestones) | 5 seeds

      Median episode: 90.9%
      Best episode: 100%

      All augmentation | Avg: 96.5% (10.62 / 11 milestones) | 5 seeds

      Median episode: 100%
      Best episode: 100%
    • Game 1, Task 1 | 12 Milestones

      No augmentation | Avg: 42.2% (5.06 / 12 milestones) | 5 seeds

      Median episode: 41.7%
      Best episode: 75%

      All augmentation | Avg: 72.2% (8.66 / 12 milestones) | 5 seeds

      Median episode: 83.3%
      Best episode: 100%

      Game 1, Task 2 | 11 Milestones

      No augmentation | Avg: 36.5% (4.02 / 11 milestones) | 5 seeds

      Median episode: 27.3%
      Best episode: 81.8%

      All augmentation | Avg: 67.5% (7.42 / 11 milestones) | 5 seeds

      Median episode: 63.6%
      Best episode: 100%

    Synthetic conditions

    Best episodes are the highest-scoring latest completed rollouts for a setting. Median episodes are selected from the middle of the score distribution for each setting

    • Game 1, Task 1 | 12 Milestones

      No augmentation | Avg: 72.3% (8.68 / 12 milestones) | 5 seeds

      Median episode: 75%
      Best episode: 100%

      Standard augmentation | Avg: 76.5% (9.18 / 12 milestones) | 5 seeds

      Median episode: 75%
      Best episode: 100%

      Streamingaugmentation | Avg: 87% (10.44 / 12 milestones) | 5 seeds

      Median episode: 100%
      Best episode: 100%

      All augmentation | Avg: 86.7% (10.40 / 12 milestones) | 5 seeds

      Median episode: 91.7%
      Best episode: 100%

      Game 1, Task 2 | 11 Milestones

      Noaugmentation | Avg: 54.9% (6.04 / 11 milestones) | 5 seeds

      Median episode: 72.7%
      Best episode: 100%

      Standard augmentation | Avg: 53.5% (5.88 / 11 milestones) | 5 seeds

      Median episode: 45.5%
      Best episode: 100%

      Streamingaugmentation | Avg: 96% (10.56 / 11 milestones) | 5 seeds

      Median episode: 100%
      Best episode: 100%

      All augmentation | Avg: 96.2% (10.58 / 11 milestones) | 5 seeds

      Median episode: 100%
      Best episode: 100%

    Real Streaming Noise conditions

    Best episodes are the highest-scoring latest completed rollouts for a setting. Median episodes are selected from the middle of the score distribution for each setting

    • Game 1, Task 2 | 12 Milestones

      No augmentation | Avg: 44.5% (4.90 / 11 milestones) | 1 seed

      Median episode: 36.4%
      Best episode: 81.8%

      All augmentation | Avg: 90% (9.90 / 11 milestones) | 1 seed

      Median episode: 90.9%
      Best episode: 100%

    Augmentation visualization

    Game 1, Task 1

    The unmodified source clip used for all comparisons in this section.

    Standard Augmentation: Color Jitter

    Per-frame color perturbations from the standard augmentation stack.

    Standard Augmentation: Random Affine

    Spatial transforms such as translation, scaling, and rotation from the standard augmentation stack.

    Streaming Augmentation: Fuzziness

    Blur-like streaming degradation that softens details over time.

    Streaming Augmentation: Ghosting

    Persistence trails that blend information from nearby frames.

    Streaming Augmentation: Pixelation

    Streaming-like block artifacts that reduce local visual fidelity.

    Streaming Augmentation: Scrubs

    Short scrub-like playback disruptions that perturb streaming continuity.

    All Streaming Augmentations

    The streaming augmentation family combined on the same source clip.

    Combined: All Augmentations

    The saved pipeline output after applying the standard augmentation stack and then the streaming augmentation stack.
    Augmentations Games Streamed Temporal Video
    Share. Facebook Twitter
    Previous ArticleDC Comics: An Absolute Batman theory about Joker that’s crazy enough to be true
    Next Article Shamita Shetty recalls being told to have a baby to cure endometriosis
    James

    Related Posts

    Acclaimed PlayStation 5 RPG Out Today on PlayStation Store

    August 21, 2026

    Save Our Game Workers: CWA Members Rally Across U.S. and Canada Against XBOX Layoffs

    August 21, 2026

    A look at Star Ocean The Second Story R on Nintendo Switch 2

    August 21, 2026

    Army unit offers troops bonus days off to play ‘Grand Theft Auto VI’ if they reenlist

    August 21, 2026

    Comments are closed.

    Our Picks

    The Odyssey becomes highest-grossing R-rated film of all time with a $1.35 billion haul, beats Deadpool & Wolverine

    August 21, 2026

    ‘The Odyssey’ becomes highest-grossing R-rated film of all time, beating ‘Deadpool & Wolverine’

    August 21, 2026

    5 TV Shows That Adapted The Story Of The Odyssey

    August 21, 2026

    Prolight + Sound Bangkok debut set to energise Southeast Asia’s pro AV and entertainment technology market

    August 21, 2026
    • Facebook
    • Twitter
    • Instagram
    • YouTube
    • TikTok
    • Telegram
    Don't Miss
    Toys & Collectibles

    Something new is coming! Spider-Man Deluxe Gift Set! Exclusive #18 for San Diego Comic

    By JamesJuly 7, 20260

    The Best Darn Toy News On The Web! Tuesday, July 07, 2026 Something new is coming! Spider-Man Deluxe Gift Set! Exclusive #18 for San Diego Comic-Con from Monogram International #SDCC July 6, 2026 Swing into action with this dynamic Spider-Man Deluxe Gift Set, perfect for fans of the friendly neighborhood hero! Retail Price: $40.00 Units…

    What To Watch In July: A Printable TV Calendar Highlighting Every Major Premiere And Finale

    July 7, 2026

    ‘Wolverine’ #10 leans into a haunted vibe with light plot progression

    July 7, 2026

    Top 5 Sales from 2026 Panini Prizm World Cup (So Far)

    July 8, 2026

    Subscribe to Updates

    Get the latest creative news from SmartMag about art & design.

    About Us
    About Us

    Comic Vibe is a pop-culture destination created for fans who live and breathe comics, movies, anime, TV shows, gaming, tech, cosplay, and collectibles.

    Our mission is to deliver engaging news, reviews, features, guides, and opinions that celebrate geek culture in all its forms. From the latest comic releases and blockbuster films to anime trends, gaming updates, cutting-edge tech, and collector culture, Comic Vibe brings everything together in one vibrant hub.

    Our Picks

    The Odyssey becomes highest-grossing R-rated film of all time with a $1.35 billion haul, beats Deadpool & Wolverine

    August 21, 2026

    ‘The Odyssey’ becomes highest-grossing R-rated film of all time, beating ‘Deadpool & Wolverine’

    August 21, 2026

    5 TV Shows That Adapted The Story Of The Odyssey

    August 21, 2026

    Subscribe to Updates

    Get the latest comics, anime, movies, TV, gaming, cosplay, and pop culture news delivered directly to your inbox. No spam—just the stories every fan should know.

    Facebook X (Twitter) Instagram YouTube TikTok
    • Home
    • Contact Us
    • Terms & Conditions
    • Advertise With Us
    • DMCA Policy
    • Privacy Policy
    • About Us
    © 2026 Comic Vibe. Designed by Comic Vibe.

    Type above and press Enter to search. Press Esc to cancel.