About
RLKit is an open-source set of externals for reinforcement learning in PureData and Max/MSP. It is implemented with the Flext cross-platform framework. It is intended ease the development of reinforcement learning solutions for robotic control and multimedia work by creators using PureData or Max/MSP. Reinforcement learning (RL) is an approach for building agent behaviors in complex environments through learning.
What is reinforcement learning?
From Wikipedia:
Reinforcement learning refers to a class of problems in machine learning which postulate an agent exploring an environment in which the agent perceives its current state and takes actions. The environment, in return, provides a reward (which can be positive or negative). Reinforcement learning algorithms attempt to find a policy for maximizing cumulative reward for the agent over the course of the problem.
Reinforcment learning has been successfully applied in a number of different fields of research, especially in robotics. For a good introduction on reinforcement learning, we suggest reading the book Reinforcement Learning: An Introduction; an online version can be found here.