Table 1.

Parameters for the AuGMEnT network.

Parameter	Value
β : Learning parameter	0.15
λ : Eligibility persistence	0.15
γ : Discount factor	0.9
α : Eligibility decay rate	1 − γλ
ϵ : Exploration rate	0.025
t* : Softmax time scale	2000 trials
m : Softmax scaling factor	10

Test dataset consists of 1, 000 random sequences, while averages are computed over 100 simulations.