Statements (14)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
research
|
| gptkbp:announced |
2021
|
| gptkbp:developedBy |
gptkb:OpenAI
|
| gptkbp:field |
gptkb:artificial_intelligence
gptkb:reinforcement_learning |
| gptkbp:focusesOn |
language-based reward specification
learning from human feedback |
| gptkbp:fullName |
gptkb:Benchmarking_Autonomous_Systems_for_Agents_with_Language_and_Task
|
| gptkbp:goal |
evaluate RL agents using natural language instructions
|
| https://www.w3.org/2000/01/rdf-schema#label |
BASALT project
|
| gptkbp:uses |
gptkb:Minecraft
|
| gptkbp:website |
https://www.aicrowd.com/challenges/neurips-2021-minerl-basalt-competition
|
| gptkbp:bfsParent |
gptkb:Darlene_Lim
|
| gptkbp:bfsLayer |
6
|