Reinforcement learningReinforcement learning (RL) is an area of machine learning concerned with how intelligent agents ought to take actions in an environment in order to maximize the notion of cumulative reward. Reinforcement learning is one of three basic machine learning paradigms, alongside supervised learning and unsupervised learning. Reinforcement learning differs from supervised learning in not needing labelled input/output pairs to be presented, and in not needing sub-optimal actions to be explicitly corrected.
Deep reinforcement learningDeep reinforcement learning (deep RL) is a subfield of machine learning that combines reinforcement learning (RL) and deep learning. RL considers the problem of a computational agent learning to make decisions by trial and error. Deep RL incorporates deep learning into the solution, allowing agents to make decisions from unstructured input data without manual engineering of the state space. Deep RL algorithms are able to take in very large inputs (e.g.
Q-learningQ-learning is a model-free reinforcement learning algorithm to learn the value of an action in a particular state. It does not require a model of the environment (hence "model-free"), and it can handle problems with stochastic transitions and rewards without requiring adaptations. For any finite Markov decision process (FMDP), Q-learning finds an optimal policy in the sense of maximizing the expected value of the total reward over any and all successive steps, starting from the current state.
BackpropagationAs a machine-learning algorithm, backpropagation performs a backward pass to adjust the model's parameters, aiming to minimize the mean squared error (MSE). In a single-layered network, backpropagation uses the following steps: Traverse through the network from the input to the output by computing the hidden layers' output and the output layer. (the feedforward step) In the output layer, calculate the derivative of the cost function with respect to the input and the hidden layers.
Temporal difference learningTemporal difference (TD) learning refers to a class of model-free reinforcement learning methods which learn by bootstrapping from the current estimate of the value function. These methods sample from the environment, like Monte Carlo methods, and perform updates based on current estimates, like dynamic programming methods. While Monte Carlo methods only adjust their estimates once the final outcome is known, TD methods adjust predictions to match later, more accurate, predictions about the future before the final outcome is known.
Artificial neural networkArtificial neural networks (ANNs, also shortened to neural networks (NNs) or neural nets) are a branch of machine learning models that are built using principles of neuronal organization discovered by connectionism in the biological neural networks constituting animal brains. An ANN is based on a collection of connected units or nodes called artificial neurons, which loosely model the neurons in a biological brain. Each connection, like the synapses in a biological brain, can transmit a signal to other neurons.
ChessChess is a board game for two players, called White and Black, each controlling an army of chess pieces in their color, with the objective to checkmate the opponent's king. It is sometimes called international chess or Western chess to distinguish it from related games, such as xiangqi (Chinese chess) and shogi (Japanese chess). The recorded history of chess goes back at least to the emergence of a similar game, chaturanga, in seventh century India.
Chess.comChess.com is an internet chess server and social networking website. The site has a freemium model in which some features are available for free, and others are available for accounts with subscriptions. Live online chess can be played against other users in daily, rapid, blitz or bullet time controls, with a number of chess variants also available. Chess versus a chess engine, computer analysis, chess puzzles and teaching resources are also offered.
Chess variantA chess variant is a game related to, derived from, or inspired by chess. Such variants can differ from chess in many different ways. "International" or "Western" chess itself is one of a family of games which have related origins and could be considered variants of each other. Chess developed from chaturanga, from which other members of this family, such as ouk chatrang, shatranj, Tamerlane chess, shogi, and xiangqi also evolved. Many chess variants are designed to be played with the equipment of regular chess.
Recurrent neural networkA recurrent neural network (RNN) is one of the two broad types of artificial neural network, characterized by direction of the flow of information between its layers. In contrast to uni-directional feedforward neural network, it is a bi-directional artificial neural network, meaning that it allows the output from some nodes to affect subsequent input to the same nodes. Their ability to use internal state (memory) to process arbitrary sequences of inputs makes them applicable to tasks such as unsegmented, connected handwriting recognition or speech recognition.
Computer chessComputer chess includes both hardware (dedicated computers) and software capable of playing chess. Computer chess provides opportunities for players to practice even in the absence of human opponents, and also provides opportunities for analysis, entertainment and training. Computer chess applications that play at the level of a chess master or higher are available on hardware from supercomputers to smart phones. Standalone chess-playing machines are also available.
Chess engineIn computer chess, a chess engine is a computer program that analyzes chess or chess variant positions, and generates a move or list of moves that it regards as strongest. A chess engine is usually a back end with a command-line interface with no graphics or windowing. Engines are usually used with a front end, a windowed graphical user interface such as Chessbase or WinBoard that the user can interact with via a keyboard, mouse or touchscreen.
Reinforcement learning from human feedbackIn machine learning, reinforcement learning from human feedback (RLHF) or reinforcement learning from human preferences is a technique that trains a "reward model" directly from human feedback and uses the model as a reward function to optimize an agent's policy using reinforcement learning (RL) through an optimization algorithm like Proximal Policy Optimization. The reward model is trained in advance to the policy being optimized to predict if a given output is good (high reward) or bad (low reward).
Deep learningDeep learning is part of a broader family of machine learning methods, which is based on artificial neural networks with representation learning. The adjective "deep" in deep learning refers to the use of multiple layers in the network. Methods used can be either supervised, semi-supervised or unsupervised.
Neural networkA neural network can refer to a neural circuit of biological neurons (sometimes also called a biological neural network), a network of artificial neurons or nodes in the case of an artificial neural network. Artificial neural networks are used for solving artificial intelligence (AI) problems; they model connections of biological neurons as weights between nodes. A positive weight reflects an excitatory connection, while negative values mean inhibitory connections. All inputs are modified by a weight and summed.
Correspondence chessCorrespondence chess is chess played by various forms of long-distance correspondence, traditionally through the postal system. Today it is usually played through a correspondence chess server, a public internet chess forum, or email. Less common methods that have been employed include fax, homing pigeon and phone. It is in contrast to (OTB) chess, where the players sit at a chessboard at the same time, or play each other in real time via the internet.
RpropRprop, short for resilient backpropagation, is a learning heuristic for supervised learning in feedforward artificial neural networks. This is a first-order optimization algorithm. This algorithm was created by Martin Riedmiller and Heinrich Braun in 1992. Similarly to the Manhattan update rule, Rprop takes into account only the sign of the partial derivative over all patterns (not the magnitude), and acts independently on each "weight".
Feedforward neural networkA feedforward neural network (FNN) is one of the two broad types of artificial neural network, characterized by direction of the flow of information between its layers. Its flow is uni-directional, meaning that the information in the model flows in only one direction—forward—from the input nodes, through the hidden nodes (if any) and to the output nodes, without any cycles or loops, in contrast to recurrent neural networks, which have a bi-directional flow.
Multilayer perceptronA multilayer perceptron (MLP) is a misnomer for a modern feedforward artificial neural network, consisting of fully connected neurons with a nonlinear kind of activation function, organized in at least three layers, notable for being able to distinguish data that is not linearly separable. It is a misnomer because the original perceptron used a Heaviside step function, instead of a nonlinear kind of activation function (used by modern networks).
Glossary of chessThis glossary of chess explains commonly used terms in chess, in alphabetical order. Some of these terms have their own pages, like fork and pin. For a list of unorthodox chess pieces, see Fairy chess piece; for a list of terms specific to chess problems, see Glossary of chess problems; for a list of named opening lines, see List of chess openings; for a list of chess-related games, see List of chess variants; for a list of terms general to board games, see Glossary of board games.
