Eligibility Trace Update

Problem

Update an accumulating eligibility trace for one state visit.

Decay every entry by gamma * lam, then add 1.0 to trace[s]. Return the new trace without mutating the input.

Hint

Decay first, then bump the visited state so its trace is exactly 1.

case 1

in: [[0,0],0,0.9,0.5]

expected: [1,0]

case 2

in: [[1,0.5],1,0.9,0.5]

expected: [0.45,1.225]

case 3

in: [[0.2,0.4,0.6],2,1,1]

expected: [0.2,0.4,1.6]

Starter codePython

def eligibility_trace_update(trace, s, gamma, lam):
    # Your code here
    pass

3 test cases · run your code against them in the editor