Reinforcement learning : industrial applications of intelligent agents

Reinforcement learning industrial applications of intelligent agents

Reinforcement learning (RL) will deliver one of the biggest breakthroughs in AI over the next decade, enabling algorithms to learn from their environment to achieve arbitrary goals. This exciting development avoids constraints found in traditional machine learning (ML) algorithms. This practical boo...

Descripción completa

Detalles Bibliográficos
Otros Autores: Winder, Phil, author (author)
Formato: Libro electrónico
Idioma:Inglés
Publicado: Beijing : O'Reilly [2021]
Edición:1st edition
Materias:
Reinforcement learning > Industrial applications.
Dynamic programming > Industrial applications.
Neural networks (Computer science)
Ver en Biblioteca Universitat Ramon Llull:https://discovery.url.edu/permalink/34CSUC_URL/1im36ta/alma991009631539006719
Tabla de Contenidos:
  • 1. Why reinforcement learning?
  • 2. Markov decision processes, dynamic programming, and Monte Carlo methods
  • 3. Temporal-difference learning, Q-learning, and n-step algorithms
  • 4. Deep Q-networks
  • 5. Policy gradient methods
  • 6. Beyond policy gradients
  • 7. Learning all possible policies with entropy methods
  • 8. Improving how an agent learns
  • Practical reinforcement learning
  • 10. Operational reinforcement learning
  • 11. Conclusions and the future.

Ejemplares similares