🏠 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

Multi-Step Distributional TD

Temporal-difference algorithm that propagates information over multiple time steps in the distribution space, improving the stability and efficiency of learning.

📖
termini

Quantile Regression in RL

Distributional approach that directly estimates the quantiles of the return distribution, offering a flexible representation without requiring prior discretization.

📖
termini

Wasserstein Metric

Distance between distributions used in distributional learning to measure the similarity between return distributions, taking into account the geometry of the reward space.

📖
termini

N-Step Return Distribution

Probability distribution of the sum of rewards over N future steps, used to accelerate information propagation in multi-step distributional algorithms.

📖
termini

Distributional Policy Evaluation

Process of estimating the complete return distribution for a given policy, rather than just its expected value, allowing for finer performance analysis.

📖
termini

Risk-Sensitive RL

Extension of distributional reinforcement learning that optimizes specific risk measures (CVaR, variance) rather than expectation alone.

📖
termini

Distributional Policy Gradient

Policy optimization algorithm that uses the complete information of the return distribution to update parameters, enabling explicit risk-reward trade-offs.

📖
termini

Distributional Actor-Critic

Architecture where the critic evaluates the return distribution rather than a single scalar value, providing a richer learning signal to the actor.

📖
termini

Distributional Dynamic Programming

Extension of dynamic programming methods that operates on value distributions, allowing more precise resolution of problems with uncertainty.

📖
termini

Atomic Support in C51

Discrete set of predefined values used as support to represent return distributions in the C51 algorithm, allowing efficient approximation of continuous distributions.

📖
termini

Distributional Bootstrap

Estimation technique where the distribution of a state is updated using the distribution of next states, preserving the stochastic structure across iterations.

📖
termini

Stability in Distributional RL

Property guaranteeing the convergence of distributional algorithms, often improved through the use of multi-step methods and appropriate projections.

📖
termini

Distributional Risk Measures

Functionals of the return distribution (Value-at-Risk, Expected Shortfall) used to characterize and optimize behavior in the face of uncertainty.

📖
termini

Multi-Step Uncertainty Propagation

Mechanism by which uncertainty about future returns is effectively propagated across multiple time horizons in the distributional framework.

📖
termini

Distributional Sampling

Sampling technique from predicted return distributions to estimate gradients and update policies in distributional algorithms.

🔍

Nessun risultato trovato