🏠 Home
Benchmark
📊 Tutti i benchmark 🦖 Dinosauro v1 🦖 Dinosauro v2 ✅ App To-Do List 🎨 Pagine libere creative 🎯 FSACB - Ultimate Showcase 🌍 Benchmark traduzione
Modelli
🏆 Top 10 modelli 🆓 Modelli gratuiti 📋 Tutti i modelli ⚙️ Kilo Code
Risorse
💬 Libreria di prompt 📖 Glossario IA 🔗 Link utili

Glossario IA

Il dizionario completo dell'Intelligenza Artificiale

162
categorie
2.032
sottocategorie
23.060
termini
📖
termini

Offline imitation learning

Learning paradigm where the agent learns to imitate expert behaviors without interacting with the environment, using only a fixed set of pre-recorded demonstrations.

📖
termini

Demonstration set

Static collection of trajectories or expert action examples used as the sole source of information for offline imitation learning.

📖
termini

Offline reinforcement learning

Reinforcement learning approach that uses only a pre-existing dataset without real-time interaction with the environment.

📖
termini

Importance sampling

Statistical technique used to correct the discrepancy between the data distribution and target policy by weighting samples according to their relative probability.

📖
termini

Distribution preservation

Constraint imposed on the learned policy to remain close to the demonstration distribution, thus avoiding risky extrapolations in unknown regions.

📖
termini

Offline trajectory

Complete sequence of states, actions, and rewards recorded from an expert policy, constituting the basic unit of learning data.

📖
termini

Expert policy

Reference strategy that generated the demonstrations, serving as a model to imitate and defining the desired optimal behavior.

📖
termini

Offline estimator

Value or policy estimation algorithm specifically designed to work with static data without requiring interaction with the environment.

📖
termini

Conservative bias correction

Bias correction approach that prioritizes safety by penalizing under-represented actions in the demonstration data.

📖
termini

Constrained imitation learning

Method incorporating explicit constraints on the divergence between the learned policy and the data distribution to ensure stability.

📖
termini

Transition set

Data structure storing tuples (state, action, next state, reward) extracted from expert trajectories for offline training.

📖
termini

Adaptive importance weighting

Dynamic weighting technology that adjusts importance weights based on confidence in data quality in different regions of the state space.

📖
termini

Coverage error

Measure quantifying the mismatch between the support of the data distribution and that of the optimal policy in offline learning.

🔍

Nessun risultato trovato