Skip to content
Saturday, July 11, 2026 HuggingFace TRL v3 TRL (Transformer Reinforcement Learning, now stylized as Transformers Reinforcement Learning) is an open-source Python library maintained by Hugging Face for... EXAONE v2 EXAONE (an acronym for EXpert AI for EveryONE) is the family of large language models and foundation models developed by LG AI Research, the artificial... Attention Is All You Need v9 "Attention Is All You Need" is the 2017 research paper that introduced the transformer, the neural network architecture that underpins virtually every modern... Vanishing Gradient Problem v8 See also: Machine learning terms The vanishing gradient problem is a difficulty in training deep neural networks where the gradients used to update the network... Momentum v6 See also: Machine learning terms, Optimizer, Gradient descent Momentum is an optimization technique that accelerates gradient descent by accumulating an... Convergence v5 Convergence in machine learning is the point at which an iterative optimization algorithm reaches a stable solution, meaning the loss function stops decreasing... Episode (Reinforcement Learning) v6 An episode in reinforcement learning is one complete sequence of interaction between an agent and its environment, starting from an initial state and ending... YaRN v5 YaRN (Yet another RoPE extensioN) is a compute-efficient method for extending the context window of large language models that use Rotary Position Embeddings... SwiGLU v5 SwiGLU (Swish-Gated Linear Unit) is the activation function used inside the feed-forward sublayer of most modern transformer large language models, including... Markov chain v4 A Markov chain is a stochastic process in which the probability of the next state depends only on the current state and not on the sequence of states that came... Temporal-difference learning v4 Temporal-difference (TD) learning is a class of model-free reinforcement learning methods that learn value-function estimates by bootstrapping: updating each... DDPM v9 Denoising Diffusion Probabilistic Models (DDPM) are a class of generative model introduced by Jonathan Ho, Ajay Jain, and Pieter Abbeel of UC Berkeley in their... Q-Function v7 The Q-function, also called the action-value function or state-action value function and written , is the function in reinforcement learning (RL) that returns... Random Forest v10 See also: Machine learning terms A random forest is a supervised machine learning algorithm that builds many decision trees on random subsets of the data and... Dense Layer v7 A dense layer, also called a fully connected (FC) layer, linear layer, or affine layer, is a layer in an artificial neural network where every input neuron is... Attention v15 See also: Machine learning terms > This article gives a high-level overview of attention as a family of mechanisms in machine learning. For deeper treatments,... Singular value decomposition v7 See also: principal component analysis, eigenvalue decomposition, linear algebra, matrix factorization, pseudoinverse, low-rank adaptation, Eckart-Young... Discount Factor v4 The discount factor, almost always written as the Greek letter (gamma), is a scalar hyperparameter in reinforcement learning that controls how much an agent... Trajectory (Reinforcement Learning) v6 A trajectory in reinforcement learning is a sequence of states, actions, and rewards that an agent experiences while interacting with an environment. Formally... Markov property v9 The Markov property is the condition that a stochastic process is memoryless: the future of the process depends only on its present state, not on the path the... Prolog v2 Prolog (a contraction of the French PROgrammation en LOGique) is a logic programming language, first implemented in 1972 by Alain Colmerauer's group at the... NuminaMath v4 NuminaMath is a family of openly licensed competition-mathematics resources developed by the non-profit Project Numina, spanning the largest public dataset of... Fairlearn v2 Fairlearn is an open-source Python toolkit for assessing and improving the fairness of machine-learning models with respect to sensitive attributes such as... Alec Radford v3 Alec Radford is an American machine learning researcher who was the first author of the papers introducing the DCGAN generative adversarial network, the... Ridge Regression v4 Ridge regression is a method of estimating the coefficients of a linear regression model by adding a penalty proportional to the sum of squared coefficients... Positional encoding v11 Positional encoding is a technique used to inject information about token order into transformer models. Because transformers process all tokens in a sequence... L2 Regularization v7 See also: machine learning terms, regularization, L1 regularization, elastic net, overfitting L2 regularization is a technique in machine learning and... Cross-Entropy Loss v5 Cross-entropy loss is the standard loss function for classification and language modeling, defined as the negative log-probability a model assigns to the... Greedy Policy v5 In reinforcement learning, a greedy policy is a decision rule that, in every state, selects the action with the highest estimated value, formally the action... Q-Learning v8 See also: Machine learning terms Q-learning is a model-free, off-policy reinforcement learning algorithm that learns the value of taking a given action in a... Empirical Risk Minimization v4 Empirical risk minimization (ERM) is the foundational principle of statistical learning theory: because the true risk (the expected loss over the unknown data... Multi-Head Self-Attention v7 Multi-head self-attention is the core sequence-mixing mechanism of the Transformer architecture: it runs several scaled dot-product attention operations... Convex Function v8 A convex function is a real-valued function whose graph curves upward into a bowl or cup shape, so that the line segment (chord) connecting any two points on... Convex Optimization v6 Convex optimization is the branch of mathematical optimization that minimizes a convex function over a convex set, a problem class with one defining advantage:... Hinge Loss v6 Hinge loss is the margin-based loss function defined as max(0, 1 - y f(x)), used to train support vector machines (SVMs) and other maximum-margin classifiers,... DQN v6 The Deep Q-Network (DQN) is a model-free, off-policy reinforcement learning algorithm that combines Q-learning with a deep neural network function... Tabular Q-Learning v4 Tabular Q-learning is the classic form of Q-learning, a model-free reinforcement learning algorithm that stores the action-value function Q(s, a) explicitly in... Bahdanau attention v7 Bahdanau attention is the first attention mechanism for neural networks, introduced in 2014 to let a sequence-to-sequence decoder soft-align to every encoder... Policy v6 See also: Reinforcement learning, Q-learning, Markov decision process In reinforcement learning (RL), a policy is the function that maps an agent's observed... Gradient Descent v9 Gradient descent is a first-order iterative optimization algorithm that minimizes a differentiable loss function by repeatedly stepping in the direction of the... Self-attention v8 Self-attention is a mechanism that lets a neural network weigh how much every element of a single input sequence should influence every other element,... Parameter update v5 See also: Machine learning terms A parameter update is the step in neural-network training where a model's trainable weights are adjusted using the gradient of... Hyperplane v5 A hyperplane is a flat, affine subspace of dimension n-1 embedded in an n-dimensional space, defined by the linear equation , where w is a normal vector and b... State-Action Value Function v6 The state-action value function, written Q^π(s, a) and also called the action-value function or Q-function, gives the expected discounted return an agent... AdaGrad v6 See also: Machine learning terms AdaGrad (short for Adaptive Gradient Algorithm) is an optimizer for gradient descent-based machine learning that gives every... Softmax v9 See also: Machine learning terms The softmax function is a mathematical function that converts a vector of real numbers, often called logits, into a... Return (Reinforcement Learning) v6 In reinforcement learning, the return (commonly denoted ) is the total cumulative reward an agent receives from time step onward, usually with future... Multi-head Latent Attention v6 Multi-head Latent Attention (MLA) is an attention mechanism for transformer models that achieves a 93.3% reduction in key-value cache size while maintaining or... Bellman Equation v8 See also: reinforcement learning, Markov decision process, Q-learning, dynamic programming, value function, Machine learning terms The Bellman equation is a... Newer Page 11 of 41 Older See also: ChatGPT, OpenAI, Prompt Engineering, Custom GPTs, GPT Store. ChatGPT is a general purpose chat assistant built by OpenAI on top of the GPT family of...
