Mammal for Retort Learning

RLS squared and L2 RL are two different approaches to reinforcement learning. RLS squared is a general function approximator, so it tends to be GRU or LSTM. That's kind of at the extreme other end of the spectrum from mammal. Mammal really has found more popularity. I feel like in this sort of few shot classification setting more recently turns out actually doing mammal for reinforcement learning is really challenging. So you need to collect some data for that. If your performance matters from the first time step of training, then RLS squares is kind of more the algorithm you would use.