CMPUT 609: Reinforcement Learning 2 Project

TD error as a heuristic for σ selection in Q(σ, λ)

Making this repository as a store for my Reinforcement Learning 2 course

The repository isn't very organized, but it was meant to be a data and experiment dump if I needed to revisit my project. The related paper is linked here: https://arxiv.org/abs/1912.10316