Multiagent Reinforcement Learning toolbox Version 1.0 This directory contains scripts demonstrating the use of the MARL toolbox. learndemo - Demonstration of plain Q-learning on a 5x5 gridworld batchdemo - Demonstration of using batch experiments alg_gui - Demonstration of various MARL algorithms on several types of gridworlds Subdirectories: /priv - Private functions used by the demonstrations. However run_algorithm and replay_algorithm can be used stand-alone.