Reinforcement learningField of machine learning The typical framing of a reinforcement learning (RL) scenario: an agent takes actions in an environment, which is interpreted into a reward and a state representation, which are fed back to the agent.In machine learning and optimal control, reinforcement learning (RL) (also known as approximate dynamic programming) is concerned with how an intelligent agent should take actions in a dynamic environment in order to maximize a reward signal.
Model-free (reinforcement learning)In reinforcement learning (RL), a model-free algorithm is an algorithm which does not estimate the transition probability distribution (and the reward function) associated with the Markov decision process (MDP), which, in RL, represents the problem to be solved. The transition probability distribution (or transition model) and the reward function are often collectively called the "model" of the environment (or MDP), hence the name "model-free".
Monte Carlo methodMonte Carlo methods, also called the Monte Carlo experiments or Monte Carlo simulations, are a broad class of computational algorithms based on repeated random sampling for obtaining numerical results, conceptualized by Polish mathematician Stanisław Ulam. The underlying concept is to use randomness to solve deterministic problems.
Markov decision processMathematical model for sequential decision making under uncertaintyA Markov decision process (MDP) is a mathematical model for sequential decision making when outcomes are uncertain. It is a type of stochastic decision process, and is often solved using the methods of stochastic dynamic programming.
Richard S. SuttonRichard Stuart SuttonFRSFRSC (born 1957 or 1958) is a Canadian computer scientist. He is a professor of computing science at the University of Alberta, fellow & Chief Scientific Advisor at the Alberta Machine Intelligence Institute, and a research scientist at Keen Technologies. Sutton is considered one of the founders of modern computational reinforcement learning. In particular, he contributed to temporal difference learning and policy gradient methods.Learning rateIn machine learning and statistics, the learning rate is a tuning parameter in an optimization algorithm that determines the step size at each iteration while moving toward a minimum of a loss function. Since it influences to what extent newly acquired information overrides old information, it metaphorically represents the speed at which a machine learning model "learns". In the adaptive control literature, the learning rate is commonly referred to as gain.
DopamineOrganic chemical that functions both as a hormone and a neurotransmitterPharmaceutical compoundDopamine (DA, a contraction of 3,4-dihydroxyphenethylamine) is a neuromodulatory molecule that plays several important roles in cells. It is an organic chemical of the catecholamine and phenethylamine families.Arthur Samuel (computer scientist)Bellman equation
Dynamic programmingProblem optimization methodFigure 1. Finding the shortest path in a graph using optimal substructure; a straight line indicates a single edge; a wavy line indicates a shortest path between the two vertices it connects (among other paths, not shown, sharing the same two vertices); the bold line is the overall shortest path from start to goal.Dynamic programming (DP) is both a mathematical optimization method and an algorithmic paradigm.Bootstrapping
Animal cognitionA crab-eating macaque using a stone tool to crack open a nutExperiments like the string-pulling task performed here by a Carib grackle provide insights into animal cognition.Animal cognition encompasses the mental capacities of non-humananimals, including insect cognition. The study of animal conditioning and learning used in this field was developed from comparative psychology.*As an Amazon Associate I earn from qualifying purchases.