Alex Ray
E441113
Alex Ray is a researcher in reinforcement learning best known for co-authoring the Hindsight Experience Replay (HER) algorithm that improves learning from sparse rewards.
All labels observed (1)
| Label | Occurrences |
|---|---|
| Alex Ray canonical | 1 |
Statements (10)
| Predicate | Object |
|---|---|
| instanceOf |
reinforcement learning algorithm
ⓘ
researcher ⓘ |
| alternativeName | HER NERFINISHED ⓘ |
| appliedIn | goal-conditioned reinforcement learning ⓘ |
| coAuthorOf | Hindsight Experience Replay NERFINISHED ⓘ |
| designedFor | sparse reward environments ⓘ |
| fieldOfWork | reinforcement learning ⓘ |
| improves | learning from sparse rewards ⓘ |
| knownFor | Hindsight Experience Replay NERFINISHED ⓘ |
| uses | hindsight relabeling of goals ⓘ |
Referenced by (1)
Full triples — surface form annotated when it differs from this entity's canonical label.