AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

TimeRewarder: Learning Dense Reward from Passive Videos via Frame-wise Temporal Distance

Yuyang Liu, Chuan Wen, Yihang Hu, Dinesh Jayaraman, Yang Gao

ICML 2026 · Reinforcement learning › Visual and representation RL · approach: Skill learning and diffusion policies

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add implicit negative sampling (reverse-ordered frame pairs) (ablation)TimeRewarder · Meta-World stick-push and basketballRL success rateImproved
add weighted sampling favoring short intervals instead of uniform (ablation)TimeRewarder · Meta-World stick-push and window-openRL success rateImproved
add two-hot discretization instead of direct regression (ablation)TimeRewarder · Meta-World basketball and disassembleRL success rateImproved
vary number of discretization bins K (ablation)TimeRewarder · Meta-WorldRL success rateNo clear effect
vary reward combination factor alpha (ablation)TimeRewarder · Meta-WorldRL success rateNo clear effect
use frame-pair relative progress instead of only-from-init, single-frame input or order prediction (ablation)TimeRewarder · Meta-WorldRL success rateImproved
add negative sampling to PROGRESSOR (ablation)PROGRESSOR · Meta-World window-close and drawer-openRL success rateMixed
use ResNet-34 instead of ViT-B backbone for VIP (ablation)VIP · Meta-WorldRL success rateMixed
combine human videos with Meta-World demonstration (ablation)TimeRewarder · Meta-World cross-domain (3 tasks)RL success rateImproved
use from-scratch ViT-B instead of CLIP-pretrained ViT-B (ablation)TimeRewarder · Meta-WorldRL success rateHurt
use TimeRewarder instead of environment dense rewardDrQ-v2 · Meta-World (10 tasks)RL success rateImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy