TY  - BOOK
AU  - Lapan, Maxim
TI  - Deep Reinforcement Learning Hands-On: Apply modern RL methods, with deep Q-networks, value iteration, policy gradients, TRPO, AlphaGo Zero and more 
SN  - 9781788834247
U1  - 006.31,LAP 
PY  - 2018///
CY  - UK
PB  - Packt
KW  - Deep Learning
N1  - What is Reinforcement Learning? (Page-1), OpenAI Gym (Page-25), Deep Learning with PyTorch (Page-49), The Cross-Entropy Method (Page-77), Tabular Learning and the Bellman Equation (Page-99), Deep Q-Networks(Page-119), DQN Extensions (Page-155), Stocks Trading Using RL (Page-217), Policy Gradients – An Alternative (Page-241), The Actor-Critic Method (Page-263), Asynchronous Advantage Actor-Critic (Page-283), Chatbots Training with RL (Page-303), Web Navigation (Page-351), Continuous Action Space (Page-399), Trust Regions – TRPO, PPO, and ACKTR (Page-427), Black-Box Optimization in RL (Page-443), Beyond Model-Free – Imagination (Page-467), AlphaGo Zero (Page-491)
ER  -