机读格式显示(MARC)
- 000 01598cam a2200325 i 4500
- 008 190819r20192018cc a b 001 0 eng d
- 040 __ |a TJU |b eng |c TJU |e rda |d TSU
- 099 __ |a CAL 022019071396
- 100 1_ |a Lapan, Maxim, |e author.
- 245 10 |a Deep reinforcement learning hands-on = |b 深度强化学习实践 / |c Maxim Lapan著.
- 264 _1 |a 南京 : |b 东南大学出版社, |c 2019.
- 300 __ |a xvi, 523 pages : |b illustrations ; |c 24 cm.
- 336 __ |a text |b txt |2 rdacontent
- 337 __ |a unmediated |b n |2 rdamedia
- 338 __ |a volume |b nc |2 rdacarrier
- 504 __ |a Includes bibliographical references and index.
- 505 0_ |a What is reinforcement learning? -- OpenAI Gym -- Deep learning with Py Torch -- The cross-entropy method -- Tabular learning and the bellman equation -- Deep Q-networks -- DQN extensions -- Stocks trading using RL -- Policy gradients : an alternative -- The actor-critic method -- Asynchronous advantage actor-critic -- Chatbots training with RL -- Web navigation -- Continuous action space -- Trust regions : TRPO, PPO, and ACKTR -- Black-box optimization in RL -- Beyond model-free : imagination -- AlphaGo Zero.
- 534 __ |p Reprint.Originally published: |c Birmingham : Packt Publishing Ltd., c2018. |z 9781788834247.
- 650 _0 |a Reinforcement learning.
- 650 _0 |a Machine learning.
- 650 _0 |a Natural language processing (Computer science)
- 650 _0 |a Artificial intelligence.
- 950 __ |a SCNU |f TP181/L299