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

Model-Based RL Advanced

RL using learned or known environment models.

Reinforcement Learning
Flow-Based Model Advanced

Exact likelihood generative models using invertible transforms.

Diffusion & Generative Models
Score-Based Model Advanced

Learns the score (∇ log p(x)) for generative sampling.

Diffusion & Generative Models
Dynamics Model Advanced

Predicts next state given current state and action.

Reinforcement Learning
RLHF Intermediate

Reinforcement learning from human feedback: uses preference data to train a reward model and optimize the policy.

Optimization
Model Registry Intermediate

Central system to store model versions, metadata, approvals, and deployment state.

Foundations & Theory
Model Tiering Intermediate

Classifying models by impact level.

Governance & Ethics
Model Stealing Intermediate

Reconstructing a model or its capabilities via API queries or leaked artifacts.

Foundations & Theory
Actor-Critic Intermediate

Combines value estimation (critic) with policy learning (actor).

AI Economics & Strategy
Reflex Agent Advanced

Simple agent responding directly to inputs.

Agents & Autonomy
Autoscaling Intermediate

Dynamic resource allocation.

AI Economics & Strategy
Control Loop Advanced

Continuous loop adjusting actions based on state feedback.

Robotics & Embodied AI
Controller Intermediate

Algorithm computing control actions.

Foundations & Theory
Self-Model Frontier

Internal representation of the agent itself.

AGI & General Intelligence
Model Risk Intermediate

Risk of incorrect financial models.

AI Economics & Strategy
DPO Intermediate

A preference-based training method optimizing policies directly from pairwise comparisons without explicit RL loops.

Optimization
SHAP Intermediate

Feature attribution method grounded in cooperative game theory for explaining predictions in tabular settings.

Foundations & Theory
Canary Tokens Intermediate

Detecting unauthorized model outputs or data leaks.

AI Economics & Strategy
Reward Model Intermediate

Model trained to predict human preferences (or utility) for candidate outputs; used in RLHF-style pipelines.

Foundations & Theory
Denoising Diffusion Probabilistic Model Advanced

Diffusion model trained to remove noise step by step.

Diffusion & Generative Models
Role Prompting Intro

Assigning a role or identity to the model.

Prompting & Instructions
Energy-Based Model Intermediate

Models that define an energy landscape rather than explicit probabilities.

Model Architectures
Pruning Intermediate

Removing weights or neurons to shrink models and improve efficiency; can be structured or unstructured.

Foundations & Theory
Boltzmann Machine Intermediate

Probabilistic energy-based neural network with hidden variables.

Model Architectures
Active Inference Frontier

Acting to minimize surprise or free energy.

World Models & Cognition
Model-Free RL Advanced

RL without explicit dynamics model.

Reinforcement Learning
Transformer Intermediate

Architecture based on self-attention and feedforward layers; foundation of modern LLMs and many multimodal models.

Transformers & LLMs
Few-Shot Learning Intermediate

Achieving task performance by providing a small number of examples inside the prompt without weight updates.

Foundations & Theory
Text-to-Speech Intermediate

Generating speech audio from text, with control over prosody, speaker identity, and style.

Speech & Audio AI
Particle Filter Intermediate

Monte Carlo method for state estimation.

Time Series

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.