Event2Reward: Learning Robotic Rewards from Progress Relations
Overview
Event2Reward is a reinforcement learning method that constructs dense shaping rewards for robots by learning from progress relations in demonstrations. It uses normalized temporal labels and within-trajectory progress relations to improve policy success across real-world tasks, outperforming sparse-reward baselines by significant margins.
From arXiv Robotics — research abstracts
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · number of tasks in LIBERO suites: 40 other · Basis not reported
“ing framewise absolute progress labels. Under the same training budgets, Event2Reward improves average policy success by 18.16 percentage points over a baseline using only sparse task rewards across 40 tasks in four LIBERO suites. On real robots, average success after 30 minutes of wall-clock training reaches 60.0% on three precise insertion tasks and 90.0% on three object manipulation tasks, exceeding the sparse-rew”
Exact source · revision 1Source owner not reported
Reported quantity · number of raw real-robot execution records: 100000 other · Basis not reported
“d, which uses normalized temporal labels to anchor the progress scale and these within-trajectory relations to constrain local changes, combining absolute and relative progress supervision. Its progress predictions serve as potentials for reward shaping. We curate an event-annotated dataset from approximately 100K raw real-robot execution records, covering successful, suboptimal, and failed executions, without requir”
Exact source · revision 1Source owner not reported
Evidence dependency changes (3)
- 2026-10-30T18:06:00.655Z · evidence updated · source revision 1. Evidence extraction was updated; current source attributions are shown above.
- 2026-10-30T17:37:36.480Z · evidence updated · source revision 1. Evidence extraction was updated; current source attributions are shown above.
- 2026-10-30T16:57:21.573Z · evidence updated · source revision 1. Evidence extraction was updated; current source attributions are shown above.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalEvent2Reward: Learning Robotic Rewards from Progress Relations
Event2Reward is a reinforcement learning method that constructs dense shaping rewards for robots by learning from progress relations in demonstrations. It uses normalized temporal labels and within-trajectory progress relations to improve policy success across real-world tasks, outperforming sparse-reward baselines by significant margins.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).