“…For h considered before we get seq(h) = 3, 2, 1, and generate <(4,3,1), (4,2,1), (3,2,1), (3,4,0), (2,4,0), (2,3,0)> with LE. Such vectors of pairs of offers derived from negotiation histories is put to a neural network along with the negotiated contracts to train it.…”