sentence11
at
SoMeSci
http://data.gesis.org/somesci/PMC5381785/sentence11
Property
Value
nif:
beginIndex
0
(xsd:integer)
nif:
broaderContext
sms:
PMC5381785
nif:
endIndex
189
(xsd:integer)
nif:
isString
Given state s, action a, reward r and next state s′, it is possible to approximate Q*(s, a) by iteratively solving the Bellman recurrence equation [1]: Qi+1(s, a) = E[r + γmaxa′Qi(s′, a′)].
rdf:
type
nif:
Context
nif:
OffsetBasedString
nif:
Sentence