PredatorReinforcementLearningSimulator

An optimal foraging simulator using Reinforcement Learning. This code is quite messy and lacks any kind of documentation and I feel horribly bad about that. This was the product of an academic excercise and time run out before this project matured to a productivity state. The code at least runs and in some cases the trajectories of the predator converged to optimality. There are some design flaws in the model itself but the learning algorithm and the NN have been extensively tested and I feel confident about their quality.