Results for "model-based"

Model-Based RL

Advanced

RL using learned or known environment models.

Model-based reinforcement learning is like having a map while exploring a new city. Instead of wandering around aimlessly, you can look at the map to plan your route and make better decisions about where to go next. In this type of learning, an AI agent first learns how the environment works—like...

405 results

Gating Network Intermediate

Chooses which experts process each token.

AI Economics & Strategy
Physics Engine Advanced

Software simulating physical laws.

Dynamics & Physics
Adaptive Optimization Intermediate

Methods like Adam adjusting learning rates dynamically.

Foundations & Theory
AlphaFold Advanced

Deep learning system for protein structure prediction.

AI in Science
Masked Language Model Intermediate

Predicts masked tokens in a sequence, enabling bidirectional context; often used for embeddings rather than generation.

Foundations & Theory
Prompt Intermediate

The text (and possibly other modalities) given to an LLM to condition its output behavior.

Prompting & Instructions
Few-Shot Prompting Intro

Multiple examples included in prompt.

Prompting & Instructions
Reflection Prompting Intro

Asking model to review and improve output.

Prompting & Instructions
World Model Frontier

Learned model of environment dynamics.

World Models & Cognition
Explainable Credit Model Intermediate

Credit models with interpretable logic.

AI Economics & Strategy
Shadow Deployment Intermediate

Running new model alongside production without user impact.

MLOps & Infrastructure
Semantic Search Intermediate

Retrieval based on embedding similarity rather than keyword overlap, capturing paraphrases and related concepts.

Foundations & Theory
Top-p Intermediate

Samples from the smallest set of tokens whose probabilities sum to p, adapting set size by context.

Foundations & Theory
Object Detection Intermediate

Identifying and localizing objects in images, often with confidence scores and bounding rectangles.

Computer Vision
On-Policy Learning Intermediate

Learning only from current policy’s data.

AI Economics & Strategy
Agent Loop Intermediate

Continuous cycle of observation, reasoning, action, and feedback.

AI Economics & Strategy
Planner-Executor Intermediate

Separates planning from execution in agent architectures.

AI Economics & Strategy
SLAM Intermediate

Simultaneous Localization and Mapping for robotics.

Computer Vision
Swarm Intelligence Advanced

Distributed agents producing emergent intelligence.

Agents & Autonomy
Saddle Plateau Intermediate

Flat high-dimensional regions slowing training.

Foundations & Theory
Latency SLA Intermediate

Guaranteed response times.

AI Economics & Strategy
Simulation Advanced

Artificial environment for training/testing agents.

Simulation & Sim-to-Real
Policy Search Advanced

Directly optimizing control policies.

Reinforcement Learning
Configuration Space Advanced

Space of all possible robot configurations.

Motion Planning & Navigation
RRT Advanced

Sampling-based motion planner.

Motion Planning & Navigation
Predictive Coding Frontier

Learning by minimizing prediction error.

World Models & Cognition
SaMD Intermediate

Software regulated as a medical device.

AI in Healthcare
Loss Function Intermediate

A function measuring prediction error (and sometimes calibration), guiding gradient-based optimization.

Foundations & Theory
Online Learning Intermediate

Learning where data arrives sequentially and the model updates continuously, often under changing distributions.

Machine Learning
Context Window Intermediate

Maximum number of tokens the model can attend to in one forward pass; constrains long-document reasoning.

Transformers & LLMs

Welcome to AI Glossary

The free, curated AI dictionary built from real, established terms and designed for a clean reading experience.

Search

Type any question or keyword into the search bar at the top.

Browse

Tap a letter in the A–Z bar to browse terms alphabetically, or filter by domain, industry, or difficulty level.

3D WordGraph

Fly around the interactive 3D graph to explore how AI concepts connect. Click any word to read its full definition.