Memory-Prediction Framework with Reinforcement Learning extension Current MPF hierarchy implementation is inspired and actually based on this paper: David Rawlinson, Gideon Kowadlo - "Generating Adaptive Behaviour within a Memory-Prediction Framework", 2012 Acknowledgments Special thanks to Mike McConnel for his project Snakey Party which I've vivisected a bit and now using as one of benchmarks for the MPF :)