This is a compact list of contextual definitions for terms relevant to machine learning applied to robotics, as used in my article on robot learning.
Agent: anything that makes decisions e.g software or a piece of machinery. The two defining characteristics of an agent are the ability to perceive its environment (through sensors) and the ability to act upon that environment (through actuators)
Affordance: an object’s property that shows the possible actions a user can take with it
Algorithm: a set of rules or instructions executed by an agent with the objective of solving a specific problem
Classification: a type of supervised learning where the output variable is discrete e.g. “Green”, “Yellow”, “Circle”, “Triangle”
Degrees of Freedom: the number of independent variables that affect the range of states in which a system can exist or the number of directions in which motion may occur
Environment: the world through which an agent moves
Gradient Descent: an optimization algorithm used in training a model by progressively estimating its local minima
Imitation Learning: a machine learning model where an agent learns a general ability by observing a human demonstration
Model: a mathematical representation of an agent’s learning process. Examples include supervised and unsupervised learning
Natural Language Processing: a branch of artificial intelligence that helps computers make sense of human language
Policy: the strategy used by an agent to take an action based on its current state. Also known as state-action mapping, a policy can be stochastic or deterministic.
Regression: a type of supervised learning where the output variable is a real value e.g. “weight”,”height”
Reinforcement Learning: a machine learning model where an agent learns from its own trial and error to arrive at a goal, without any human intervention or training data.
State: a representation of an agent’s idea of the world
Supervised Learning: a machine learning model where an agent learns a desired task from labeled data. The agent is trained with input-output data pairs that contain the correct solution for the desired task. It can either be applied to either classification or regression problems
Training: the process of teaching an agent by feeding it data
Visual Motor Skills: skills that require continual visual feedback to execute an action