HER
E441111
HER is a reinforcement learning technique that improves learning from sparse rewards by reinterpreting failed experiences as successful ones for alternative goals.
All labels observed (1)
| Label | Occurrences |
|---|---|
| HER canonical | 3 |
How this entity was disambiguated
This entity first appeared as the object of triple T4470521 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: HER Context triple: [Hindsight Experience Replay, abbreviation, HER]
-
A.
HER
HER is the commonly used abbreviation for the Harvard Educational Review, a scholarly journal focused on education research and policy.
-
B.
HER
HER is the official herbarium code assigned to the Berggarten botanical collection, used in scientific and taxonomic references.
-
C.
Her
Her is a 2013 science-fiction romantic drama film directed by Spike Jonze that explores a man's emotional relationship with an advanced artificial intelligence operating system.
-
D.
Her
"Her" is a lesser-known work by American poet, painter, and City Lights Books co-founder Lawrence Ferlinghetti, reflecting his characteristic Beat-influenced, avant-garde literary style.
-
E.
Her
"Her" is a soulful R&B song by American singer-songwriter SiR, known for its smooth production and introspective lyrics about love and vulnerability.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: HER Target entity description: HER is a reinforcement learning technique that improves learning from sparse rewards by reinterpreting failed experiences as successful ones for alternative goals.
-
A.
HER
HER is the commonly used abbreviation for the Harvard Educational Review, a scholarly journal focused on education research and policy.
-
B.
HER
HER is the official herbarium code assigned to the Berggarten botanical collection, used in scientific and taxonomic references.
-
C.
Her
Her is a 2013 science-fiction romantic drama film directed by Spike Jonze that explores a man's emotional relationship with an advanced artificial intelligence operating system.
-
D.
Her
"Her" is a lesser-known work by American poet, painter, and City Lights Books co-founder Lawrence Ferlinghetti, reflecting his characteristic Beat-influenced, avant-garde literary style.
-
E.
Her
"Her" is a soulful R&B song by American singer-songwriter SiR, known for its smooth production and introspective lyrics about love and vulnerability.
- F. None of above. chosen
Statements (42)
| Predicate | Object |
|---|---|
| instanceOf |
reinforcement learning technique
ⓘ
reinforcement learning technique ⓘ |
| abbreviation | HER ⓘ |
| addresses | sparse reward problem ⓘ |
| aimsTo |
improve learning stability in sparse reward settings
ⓘ
reduce sample complexity in goal-based tasks ⓘ |
| appliedTo |
goal-conditioned reinforcement learning
ⓘ
multi-goal reinforcement learning ⓘ |
| assumes | environment with goal space ⓘ |
| benefits |
navigation tasks with sparse rewards
ⓘ
robotic manipulation tasks ⓘ |
| category | off-policy data augmentation method ⓘ |
| commonlyCombinedWith |
DDPG
ⓘ
Deep Deterministic Policy Gradient ⓘ
linked to:
DDPG
|
| coreIdea |
reinterpret failed experiences as successful ones for alternative goals
ⓘ
relabelling goals in past trajectories ⓘ |
| describedIn | paper "Hindsight Experience Replay" ⓘ |
| fullName | Hindsight Experience Replay ⓘ |
| improves |
learning from sparse rewards
ⓘ
sample efficiency in reinforcement learning ⓘ |
| inspired |
extensions such as CHER and ARCHER
ⓘ
subsequent goal relabelling methods ⓘ |
| introducedBy |
Alex Ray
ⓘ
Bob McGrew ⓘ Filip Wolski ⓘ Jonas Schneider ⓘ Josh Tobin ⓘ Marcin Andrychowicz ⓘ OpenAI researchers ⓘ Peter Welinder ⓘ Rachel Fong ⓘ |
| introducedIn | 2017 ⓘ |
| modifies | stored transitions with alternative goals ⓘ |
| operatesOn | off-policy reinforcement learning algorithms ⓘ |
| publishedAt |
NIPS 2017
ⓘ
linked to:
NeurIPS
Neural Information Processing Systems ⓘ
linked to:
NeurIPS
|
| relatedTo |
goal relabelling
ⓘ
universal value function approximators ⓘ |
| requires | goal-conditioned reward function ⓘ |
| typeOf | model-free reinforcement learning enhancement ⓘ |
| usedIn | reinforcement learning ⓘ |
| uses | experience replay buffer ⓘ |
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: HER Description of subject: HER is a reinforcement learning technique that improves learning from sparse rewards by reinterpreting failed experiences as successful ones for alternative goals.
Referenced by (3)
Full triples — surface form annotated when it differs from this entity's canonical label.