A block of game history from a full trajectories. The horizons of Atari games are quite large. Split the whole trajectory into several histor

Reference : Data-Efficient Reinforcement Learning with Self-Predictive Representations Thanks to Repo: https://github.com/mila-iqia/spr.git

Reference : DISTRIBUTED PRIORITIZED EXPERIENCE REPLAY Algo. 1 and Algo. 2 in Page-3 of (https://arxiv.org/pdf/1803.00933.pdf