Contacto
Como comprar
Entrega
Guia de compras
Inglês
118 b
Até 30 dias para devoluções
Os clientes também compraram
Reinforcement learning is the problem faced by an§agent that must learn behavior through§trial-and-error interactions with a dynamic§environment. Usually, the problem to be solved§contains subtasks that repeat at different regions of§the state space. Without any guidance§an agent has to learn the solutions of all subtask§instances independently, which in turn degrades the§performance of the learning process. In this work, we§propose two novel approaches for building the§connections between different regions of the search§space. The first approach efficiently discovers§abstractions in the form of conditionally terminating§sequences and represents these abstractions compactly§as a single tree structure; this structure is then§used to determine the actions to be executed by the§agent. In the second approach, a similarity function§between states is defined based on the number of§common action sequences; by using this similarity§function, updates on the action-value function of a§state are re ected to all similar states that allows§experience acquired during learning be applied to a§broader context. The effectiveness of both approaches§is demonstrated empirically over various domains.
Sobre o livro
Inglês
Ofereça este livro hoje
É fácil
1 Adicione ao carrinho e escolha Entregar como presente ao finalizar a compra 2 Receberá um vale 3 O livro chegará ao endereço do destinatárioTambém pode estar interessado em
/
Capa mole
14.05
€
/
Capa mole
24.27
€
/
Capa mole
15.57
€
/
Capa mole
12.33
€
/
Livro de capa dura
90.93
€
Olá! Sou o Libroamiko, o seu conselheiro de livros.
Como posso ajudar?