RC2_LEARNING_SET_DUPLICATE

<set> is the same search as learning set <n>.

What it means

Two learning sets that describe the same search are one set shown twice. This includes a set equal to learning set 1 — which, when learning_set_1 is not written, is the strategy’s own Param ranges. A set that only fixes a switch at its default, for example, changes nothing.

Why it happens

Fixing a switch at the value it already has:

class NoChange(Strategy):
    trade = Symbol()
    sizing = FixedCapital()
    fast = Param(10, min=2, max=100, opt_min=5, opt_max=30)
    slow = Param(30, min=10, max=200, opt_min=20, opt_max=80, opt_step=5)
    offset = Param(0.01, min=0.0, max=1.0)
    use_filter = Param(False)

    learning_set_2 = LearningSet(use_filter=False)

    def execute(self):
        f = SMA(self.fast, on=self.trade)
        s = SMA(self.slow, on=self.trade)
        if f.value > s.value and self.trade.is_flat:
            self.buy(self.trade)

How to fix it

Change at least one parameter, or remove the set.

class RealChange(Strategy):
    trade = Symbol()
    sizing = FixedCapital()
    fast = Param(10, min=2, max=100, opt_min=5, opt_max=30)
    slow = Param(30, min=10, max=200, opt_min=20, opt_max=80, opt_step=5)
    offset = Param(0.01, min=0.0, max=1.0)
    use_filter = Param(False)

    learning_set_2 = LearningSet(use_filter=True)

    def execute(self):
        f = SMA(self.fast, on=self.trade)
        s = SMA(self.slow, on=self.trade)
        if f.value > s.value and self.trade.is_flat:
            self.buy(self.trade)

Learning sets
RC2_LEARNING_SET_NO_SEARCH — a set where nothing is searched.