Triple

T18629576
Position Surface form Disambiguated ID Type / Status
Subject Q-learning E455376 entity
Predicate hasKeyEquation P14117 FINISHED
Object Q(s,a) ← Q(s,a) + α[r + γ max_{a'} Q(s',a') − Q(s,a)] LITERAL FINISHED

Provenance (2 batches)

Stage Batch ID Job type Status
creating batch_69d8d38cc7948190a55ea64e5638994e elicitation completed
NER batch_69e54f06f4a081909b64f33814577488 ner completed
Created at: April 10, 2026, 11:46 a.m.