{"id":1173837,"date":"2026-07-10T08:33:15","date_gmt":"2026-07-10T15:33:15","guid":{"rendered":"https:\/\/find.codeghost.online\/en-us\/research\/?post_type=msr-blog-post&p=1173837"},"modified":"2026-07-20T15:57:16","modified_gmt":"2026-07-20T22:57:16","slug":"temporal-augmentations-for-streamed-video-games-supplementary-material","status":"publish","type":"msr-blog-post","link":"https:\/\/find.codeghost.online\/en-us\/research\/articles\/temporal-augmentations-for-streamed-video-games-supplementary-material\/","title":{"rendered":"Temporal Augmentations for Streamed Video Games: Supplementary Material"},"content":{"rendered":"\n

This supplementary website accompanies the paper \u201cAugmentations for Robust and Efficient Imitation Learning in Streamed Video Games<\/em>,” 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.<\/p>\n\n\n\n

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.<\/p>\n\n\n\n

\n
Get the code<\/a><\/div>\n\n\n\n
Read the paper<\/a><\/div>\n<\/div>\n\n\n\n

Representative rollouts<\/h2>\n\n\n\n

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.<\/p>\n\n\n\n\n\n

Clean conditions<\/h3>\n\n\n\n

Representative median and best rollouts are shown for each available method in this setting.<\/p>\n\n\n\n\n\n

\n

Game 1, Task 1 | 12 Milestones<\/h4>\n\n\n\n
<\/div>\n\n\n\n
\n
\n
<\/div>\n\n\n\n

No augmentation<\/strong> | Avg. 76.7% (9.20 \/ 12 milestones) | 5 seeds<\/p>\n\n\n\n