最新章節(jié)

• Leave a review - let other readers know what you think
• Other Books You May Enjoy
• Summary
• ROUGE
• What is BLEU score and what does it do?
• BLEU

• Leave a review - let other readers know what you think 更新時(shí)間：2021-08-27 18:52:42
• Other Books You May Enjoy
• Summary
• ROUGE
• What is BLEU score and what does it do?
• BLEU
• Scoring mechanism in sequential models in NLP
• Deterministic policy gradients
• Trust region policy optimization
• Continuous action space algorithms
• Further topics in Reinforcement Learning
• Summary
• Mixed objective using self-critical policy learning
• Deep residual coattention encoder
• Mixed objective and deep residual coattention for Question Answering
• Text question answering
• Mixed training objective function
• Policy learning
• Supervised learning with teacher forcing
• Hybrid learning objective
• Token generation and pointer
• Intra-decoder attention
• Intra-temporal attention on input sequence while decoding
• Neural intra-attention model
• Deep reinforced model for Abstractive Summarization
• Text summarization
• Deep Reinforcement Learning in NLP
• Summary
• Training specifics
• Model and training
• Reward
• Actions
• State
• Hierarchical object detection model
• Single Shot Detector
• You Look Only Once
• Faster R-CNN
• Fast R-CNN
• Spatial pyramid pooling networks
• Region-based convolution neural networks
• Related works
• Hierarchical object detection with deep reinforcement learning
• Reinforcement Learning in Image Processing
• Summary
• Real-time bidding by reinforcement learning in display advertising
• Bidding strategies of advertisers
• Adwords
• Search-advertisement management
• Sponsored-search advertisements
• Business models used in advertising
• Computational advertising challenges and bidding strategies
• Deep Reinforcement Learning in Ad Tech
• Summary
• Key takeaways
• Practical challenges for robotic reinforcement learning
• Open questions
• Open questions and practical challenges
• What's the final objective a robot wants to achieve?
• Issues due to model uncertainty
• Real-world challenges
• High dimensionality problem
• Challenges in robot reinforcement learning
• Evolution of reinforcement learning
• Reinforcement learning in robotics
• Reinforcement Learning in Robotics
• Summary
• Further improvements
• Reinforcement learning
• Data preparation
• Problem definition
• Introduction
• Financial Portfolio Management
• Summary
• DeepTraffic – MIT simulator for autonomous driving
• Planning
• Recurrent temporal aggregation
• Spatial features
• Sensor fusion
• Spatial aggregation
• Proposed frameworks for autonomous driving
• Why reinforcement learning ?
• Creating autonomous driving agents
• Reinforcement learning for autonomous driving
• Machine learning for autonomous driving
• Reinforcement Learning in Autonomous Driving
• Summary
• Training process in AlphaGo Zero
• Architecture and properties of AlphaGo Zero
• AlphaGo Zero
• Energy consumption analysis – Lee Sedol versus AlphaGo
• Architecture and properties of AlphaGo
• Monte Carlo Tree Search
• AlphaGo – mastering Go
• Why is the game tree approach no good for Go?
• How did DeepBlue defeat Gary Kasparov?
• Go versus chess
• What is Go?
• AlphaGo – Reinforcement Learning at Its Best
• Summary
• How is reinforcement learning better?
• Deep autoencoder
• Reinforcement learning in RTS gaming
• Why reinforcement learning?
• Drawbacks to real-time strategy games
• Online case-based planning
• Reinforcement learning and other approaches
• Real-time strategy games
• Robo Everything – Real Strategy Gaming
• Summary
• A3C for Pong-v0 in OpenAI gym
• Asynchronous advantage actor critic
• Asynchronous n-step Q-learning
• Asynchronous one-step SARSA
• Asynchronous one-step Q-learning
• Why asynchronous methods?
• Asynchronous Methods
• Summary
• SARSA algorithm for mountain car problem in OpenAI gym
• The SARSA algorithm
• The Monte Carlo Tree Search
• Minimax and game trees
• The Monte Carlo tree search algorithm
• Deep Q-network for Atari Breakout in OpenAI gym
• Deep Q-network for Cartpole problem in OpenAI gym
• Deep Q-network for mountain car problem in OpenAI gym
• Dueling DQN
• Double DQN
• Advancements in deep Q-networks and beyond
• Separate target network to compute the target Q-values
• Use of experience replay
• Using a convolution neural network instead of a single layer neural network
• Deep Q-networks
• Q-learning for the mountain car problem in OpenAI gym
• The exploration exploitation dilemma
• Q-learning
• On-policy and off-policy learning
• Temporal difference learning
• Monte Carlo learning
• Model based learning and model free learning
• Why reinforcement learning?
• Q-Learning and Deep Q-Networks
• Summary
• Agent learning pong using policy gradients
• Vanilla policy gradient
• Using a baseline to reduce variance
• Actor-critic algorithms
• The Monte Carlo policy gradient
• Policy gradients
• TD() rule
• TD(0) rule
• TD(1) rule
• Temporal difference rule
• Policy Gradient Theorem
• Policy objective functions
• Example 2 - state aliased grid-world
• Example 1 - rock paper scissors
• Why stochastic policy?
• Why policy optimization methods?
• The policy optimization method
• Policy Gradients
• Summary
• Training the FrozenLake-v0 environment using MDP
• Value iteration in POMDPs
• State estimation
• Partially observable Markov decision processes
• Policy iteration
• An example of value iteration using the Bellman equation
• Solving the Bellman equation to find policies
• The Bellman equations
• Utility of sequences
• The infinite horizons
• The sequence of rewards - assumptions
• Policy
• Rewards
• Transition model
• Actions
• The S state set
• The Markov property
• Markov decision processes
• Markov Decision Process
• Summary
• Using the Q-Network for real-world applications
• The Epsilon-Greedy approach
• Q-Learning
• Programming an agent using an OpenAI Gym environment
• Understanding an OpenAI Gym environment
• The OpenAI Gym
• Training Reinforcement Learning Agents Using OpenAI Gym
• Summary
• Libratus
• The AlphaGo program
• Google DeepMind
• Pieter Abbeel
• David Silver
• The pioneers and breakthroughs in reinforcement learning
• An introduction to OpenAI Gym
• Basic computations in TensorFlow
• Introduction to TensorFlow and OpenAI Gym
• Asynchronous advantage actor-critic
• The Q-learning approach to reinforcement learning
• The policy model for optimality
• The value function for optimality
• Optimality criteria
• Basic terminologies and conventions
• Reinforcement learning
• Overcoming the limitations of deep learning
• The exploding gradient problem
• The vanishing gradient problem
• Limitations of deep learning
• The Inception model
• The VGG-Net model
• The AlexNet model
• The LeNet-5 convolutional neural network
• Convolutional neural networks
• Long Short Term Memory Networks
• Recurrent neural networks
• The neural network model
• Why do we use xavier initialization?
• What is xavier initialization?
• Steps to solve logistic regression using gradient descent
• The computational graph
• The gradient descent algorithm
• The cost function
• Objective
• Notation
• Logistic regression as a neural network
• How to choose the right activation function
• The rectified linear unit function
• The softmax function
• The tanh function
• The sigmoid function
• Activation functions for deep learning
• Deep learning
• Deep Learning – Architectures and Frameworks
• Reviews
• Get in touch
• Conventions used
• Download the color images
• Download the example code files
• To get the most out of this book
• What this book covers
• Who this book is for
• Preface
• Packt is searching for authors like you
• About the reviewer
• About the author
• Contributors
• PacktPub.com
• Why subscribe?
• Packt Upsell
• Reinforcement Learning with TensorFlow
• Copyright and Credits
• Title Page
• 封面

• 封面
• Title Page
• Copyright and Credits
• Reinforcement Learning with TensorFlow
• Packt Upsell
• Why subscribe?
• PacktPub.com
• Contributors
• About the author
• About the reviewer
• Packt is searching for authors like you
• Preface
• Who this book is for
• What this book covers
• To get the most out of this book
• Download the example code files
• Download the color images
• Conventions used
• Get in touch
• Reviews
• Deep Learning – Architectures and Frameworks
• Deep learning
• Activation functions for deep learning
• The sigmoid function
• The tanh function
• The softmax function
• The rectified linear unit function
• How to choose the right activation function
• Logistic regression as a neural network
• Notation
• Objective
• The cost function
• The gradient descent algorithm
• The computational graph
• Steps to solve logistic regression using gradient descent
• What is xavier initialization?
• Why do we use xavier initialization?
• The neural network model
• Recurrent neural networks
• Long Short Term Memory Networks
• Convolutional neural networks
• The LeNet-5 convolutional neural network
• The AlexNet model
• The VGG-Net model
• The Inception model
• Limitations of deep learning
• The vanishing gradient problem
• The exploding gradient problem
• Overcoming the limitations of deep learning
• Reinforcement learning
• Basic terminologies and conventions
• Optimality criteria
• The value function for optimality
• The policy model for optimality
• The Q-learning approach to reinforcement learning
• Asynchronous advantage actor-critic
• Introduction to TensorFlow and OpenAI Gym
• Basic computations in TensorFlow
• An introduction to OpenAI Gym
• The pioneers and breakthroughs in reinforcement learning
• David Silver
• Pieter Abbeel
• Google DeepMind
• The AlphaGo program
• Libratus
• Summary
• Training Reinforcement Learning Agents Using OpenAI Gym
• The OpenAI Gym
• Understanding an OpenAI Gym environment
• Programming an agent using an OpenAI Gym environment
• Q-Learning
• The Epsilon-Greedy approach
• Using the Q-Network for real-world applications
• Summary
• Markov Decision Process
• Markov decision processes
• The Markov property
• The S state set
• Actions
• Transition model
• Rewards
• Policy
• The sequence of rewards - assumptions
• The infinite horizons
• Utility of sequences
• The Bellman equations
• Solving the Bellman equation to find policies
• An example of value iteration using the Bellman equation
• Policy iteration
• Partially observable Markov decision processes
• State estimation
• Value iteration in POMDPs
• Training the FrozenLake-v0 environment using MDP
• Summary
• Policy Gradients
• The policy optimization method
• Why policy optimization methods?
• Why stochastic policy?
• Example 1 - rock paper scissors
• Example 2 - state aliased grid-world
• Policy objective functions
• Policy Gradient Theorem
• Temporal difference rule
• TD(1) rule
• TD(0) rule
• TD() rule
• Policy gradients
• The Monte Carlo policy gradient
• Actor-critic algorithms
• Using a baseline to reduce variance
• Vanilla policy gradient
• Agent learning pong using policy gradients
• Summary
• Q-Learning and Deep Q-Networks
• Why reinforcement learning?
• Model based learning and model free learning
• Monte Carlo learning
• Temporal difference learning
• On-policy and off-policy learning
• Q-learning
• The exploration exploitation dilemma
• Q-learning for the mountain car problem in OpenAI gym
• Deep Q-networks
• Using a convolution neural network instead of a single layer neural network
• Use of experience replay
• Separate target network to compute the target Q-values
• Advancements in deep Q-networks and beyond
• Double DQN
• Dueling DQN
• Deep Q-network for mountain car problem in OpenAI gym
• Deep Q-network for Cartpole problem in OpenAI gym
• Deep Q-network for Atari Breakout in OpenAI gym
• The Monte Carlo tree search algorithm
• Minimax and game trees
• The Monte Carlo Tree Search
• The SARSA algorithm
• SARSA algorithm for mountain car problem in OpenAI gym
• Summary
• Asynchronous Methods
• Why asynchronous methods?
• Asynchronous one-step Q-learning
• Asynchronous one-step SARSA
• Asynchronous n-step Q-learning
• Asynchronous advantage actor critic
• A3C for Pong-v0 in OpenAI gym
• Summary
• Robo Everything – Real Strategy Gaming
• Real-time strategy games
• Reinforcement learning and other approaches
• Online case-based planning
• Drawbacks to real-time strategy games
• Why reinforcement learning?
• Reinforcement learning in RTS gaming
• Deep autoencoder
• How is reinforcement learning better?
• Summary
• AlphaGo – Reinforcement Learning at Its Best
• What is Go?
• Go versus chess
• How did DeepBlue defeat Gary Kasparov?
• Why is the game tree approach no good for Go?
• AlphaGo – mastering Go
• Monte Carlo Tree Search
• Architecture and properties of AlphaGo
• Energy consumption analysis – Lee Sedol versus AlphaGo
• AlphaGo Zero
• Architecture and properties of AlphaGo Zero
• Training process in AlphaGo Zero
• Summary
• Reinforcement Learning in Autonomous Driving
• Machine learning for autonomous driving
• Reinforcement learning for autonomous driving
• Creating autonomous driving agents
• Why reinforcement learning ?
• Proposed frameworks for autonomous driving
• Spatial aggregation
• Sensor fusion
• Spatial features
• Recurrent temporal aggregation
• Planning
• DeepTraffic – MIT simulator for autonomous driving
• Summary
• Financial Portfolio Management
• Introduction
• Problem definition
• Data preparation
• Reinforcement learning
• Further improvements
• Summary
• Reinforcement Learning in Robotics
• Reinforcement learning in robotics
• Evolution of reinforcement learning
• Challenges in robot reinforcement learning
• High dimensionality problem
• Real-world challenges
• Issues due to model uncertainty
• What's the final objective a robot wants to achieve?
• Open questions and practical challenges
• Open questions
• Practical challenges for robotic reinforcement learning
• Key takeaways
• Summary
• Deep Reinforcement Learning in Ad Tech
• Computational advertising challenges and bidding strategies
• Business models used in advertising
• Sponsored-search advertisements
• Search-advertisement management
• Adwords
• Bidding strategies of advertisers
• Real-time bidding by reinforcement learning in display advertising
• Summary
• Reinforcement Learning in Image Processing
• Hierarchical object detection with deep reinforcement learning
• Related works
• Region-based convolution neural networks
• Spatial pyramid pooling networks
• Fast R-CNN
• Faster R-CNN
• You Look Only Once
• Single Shot Detector
• Hierarchical object detection model
• State
• Actions
• Reward
• Model and training
• Training specifics
• Summary
• Deep Reinforcement Learning in NLP
• Text summarization
• Deep reinforced model for Abstractive Summarization
• Neural intra-attention model
• Intra-temporal attention on input sequence while decoding
• Intra-decoder attention
• Token generation and pointer
• Hybrid learning objective
• Supervised learning with teacher forcing
• Policy learning
• Mixed training objective function
• Text question answering
• Mixed objective and deep residual coattention for Question Answering
• Deep residual coattention encoder
• Mixed objective using self-critical policy learning
• Summary
• Further topics in Reinforcement Learning
• Continuous action space algorithms
• Trust region policy optimization
• Deterministic policy gradients
• Scoring mechanism in sequential models in NLP
• BLEU
• What is BLEU score and what does it do?
• ROUGE
• Summary
• Other Books You May Enjoy
• Leave a review - let other readers know what you think 更新時(shí)間：2021-08-27 18:52:42