#a2c

god i wish i spent more time on those uc essays wtf was i even writing jfc

Because of course it knows me best, right? Well, it looks like my chances aren't that great.

Challenging the memory of RL agents

Reinforcement learning agents are usually trained to maximize their rewards by taking actions in an environment following a Markov Decision Process (MDP). A Markov Decision Process is simply a model that defines the state of an environment by its current state, actions, and rewards, including also its possible future states. MDP process The key point is that agents know information from the…