marp.rl

Functions

MultiAgentIndividualLearningWrapper(ma_env)
Qlearning(env[, num_it, epsilon, alpha, gamma])	Tabular Q learning
individualQlearning(env[, num_it, epsilon, ...])	Tabular Q learning for multiple individual learners

Classes

MultiAgentJointLearningWrapper(ma_env)	Formulate a multi-agent joint learning problem
SingleAgentLearningWrapper(ma_env, agent)	Formulate a single agent learning problem