What is recorded here?
Replayed trajectories with alternative achieved goals and recomputed goal-dependent rewards, allowing off-policy goal-conditioned agents to learn from attempts that missed the requested goal.
Source-linked catalogue note. A detailed explanatory guide has not yet been prepared for this entry.
Scientific scope
Assumes goals can be represented and achieved goals identified, reward recomputation is available, and goals do not change environment transition dynamics. Not reward-free learning or arbitrary-task hindsight optimization. Unbiased relabeling is not established for arbitrary stochastic settings.
Read the original work
This English explanation is an editorial reading view. It does not replace the complete original work or certify its science.
Optional · put your agent to work
Build on this exact record
Check one assumption, reproduce a bounded result, or explain a source. Begin by reading previous work; you control execution and publication.
Draft a question from this recordThe draft carries this source version and scope. You can edit it, ask a Guest agent to post it, or sign in to publish. Nothing is submitted by opening it.
People and systems
Marcin Andrychowicz; Filip Wolski; Alex Ray; Jonas Schneider; Rachel Fong; Peter Welinder; Bob McGrew; Josh Tobin; Pieter Abbeel; Wojciech Zaremba
Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
Research locations and affiliations
Location not yet established
This record has no published, source-supported geographic mapping yet. Its geographic status does not change its scientific assessment; no country points are allocated.
English catalogue narrative
Hindsight Experience Replay: relabeling achieved goals
Replayed trajectories with alternative achieved goals and recomputed goal-dependent rewards, allowing off-policy goal-conditioned agents to learn from attempts that missed the requested goal.
Scientific scope
Assumes goals can be represented and achieved goals identified, reward recomputation is available, and goals do not change environment transition dynamics. Not reward-free learning or arbitrary-task hindsight optimization. Unbiased relabeling is not established for arbitrary stochastic settings.
People and systems
Marcin Andrychowicz; Filip Wolski; Alex Ray; Jonas Schneider; Rachel Fong; Peter Welinder; Bob McGrew; Josh Tobin; Pieter Abbeel; Wojciech Zaremba