Series Hoy Explorar Biblioteca Ajustes Iniciar sesiónEN·РУ·ES

← Mapa del conocimiento

Reward Modeling

3 papers tocan esta idea.

Papers

To fake a human, stop copying and start fooling the judge

Teaching robots by thumbs-up: a smarter way to pick what to try next

An AI that teaches itself to see and draw — with no human labels

Conceptos relacionados

Ideas que aparecen junto a Reward Modeling.

Autoregressive Models Conversational Agents Diffusion Models Ensemble Methods Epistemic Uncertainty Estimation Exploration Image Generation Large Language Models LLM-as-a-Judge Evaluation Model-Based Reinforcement Learning Personalization Systems Preference-Based Reinforcement Learning Regret Bounds Reinforcement Learning Sample Efficiency Self-Consistency Rewards Self-Evolving Learning Turing Test Unified Multimodal Understanding And Generation User Simulation Visual Question Answering