🏠 Hem
Benchmarkar
📊 Alla benchmarkar 🦖 Dinosaur v1 🦖 Dinosaur v2 ✅ To-Do List-applikationer 🎨 Kreativa fria sidor 🎯 FSACB - Ultimata uppvisningen 🌍 Översättningsbenchmark
Modeller
🏆 Topp 10 modeller 🆓 Gratis modeller 📋 Alla modeller ⚙️ Kilo Code
Resurser
💬 Promptbibliotek 📖 AI-ordlista 🔗 Användbara länkar

AI-ordlista

Den kompletta ordlistan över AI

162
kategorier
2 032
underkategorier
23 060
termer
📂
underkategorier

Distributional Value Functions

Modeling value functions as full distributions rather than scalars.

14 termer
📂
underkategorier

Categorical DQN

Algorithm using a discrete categorical representation of the return distribution.

14 termer
📂
underkategorier

Quantile Regression DQN

Approach using quantile regression to directly learn the quantiles of the distribution.

10 termer
📂
underkategorier

Risk-Sensitive Learning

Using full distributions to model risk preferences.

7 termer
📂
underkategorier

Gradient de Politique Distributionnel

Extension des méthodes de gradient de politique aux approches distributionnelles.

10 termer
📂
underkategorier

Uncertainty Estimation

Uncertainty quantification in predictions via the return distribution.

14 termer
📂
underkategorier

Multi-Step Distributional RL

Extension of multi-step methods to the distributional framework for better stability.

15 termer
📂
underkategorier

Continuous Distributional RL

Application of distributional methods to continuous action spaces.

19 termer
📂
underkategorier

Distributional Actor-Critic

Combination of distributional approaches with actor-critic methods.

16 termer
📂
underkategorier

Distributional Model-Based RL

Integration of distributions in model-based reinforcement learning methods.

17 termer
📂
underkategorier

Hierarchical Distributional RL

Application of distributional concepts to hierarchical decision structures.

11 termer
📂
underkategorier

Transfert d'Apprentissage Distributionnel

Utilisation des distributions pour améliorer le transfert de connaissances entre tâches.

9 termer
🔍

Inga resultat hittades