Deep Learning and Neural Networks

  1. Deep Reinforcement Learning
    1. Reinforcement Learning Fundamentals
      1. Agent-Environment Interaction
        1. States, Actions, and Rewards
          1. State Space
            1. Action Space
              1. Reward Function
              2. Markov Decision Processes
                1. Markov Property
                  1. Transition Probabilities
                  2. Policies and Value Functions
                    1. Policy Definition
                      1. State Value Function
                        1. Action Value Function
                        2. Exploration vs. Exploitation
                          1. Multi-Armed Bandit Problem
                            1. Epsilon-Greedy Strategy
                          2. Value-Based Methods
                            1. Q-Learning Algorithm
                              1. Temporal Difference Learning
                                1. Q-Table Updates
                                2. Deep Q-Networks (DQN)
                                  1. Neural Network Q-Function Approximation
                                    1. DQN Architecture
                                      1. Training Procedure
                                      2. DQN Improvements
                                        1. Experience Replay
                                          1. Replay Buffer Mechanism
                                            1. Breaking Temporal Correlations
                                            2. Target Networks
                                              1. Stable Target Values
                                                1. Periodic Updates
                                                2. Double DQN
                                                  1. Dueling DQN
                                                    1. Prioritized Experience Replay
                                                  2. Policy-Based Methods
                                                    1. Policy Gradient Theorem
                                                      1. REINFORCE Algorithm
                                                        1. Monte Carlo Policy Gradient
                                                          1. Baseline Subtraction
                                                          2. Actor-Critic Methods
                                                            1. Actor and Critic Roles
                                                              1. Advantage Function
                                                                1. Asynchronous Advantage Actor-Critic (A3C)
                                                                2. Proximal Policy Optimization (PPO)
                                                                  1. Clipped Surrogate Objective
                                                                    1. Trust Region Methods
                                                                  2. Model-Based Reinforcement Learning
                                                                    1. Environment Model Learning
                                                                      1. Planning with Learned Models
                                                                        1. Model-Predictive Control
                                                                        2. Multi-Agent Reinforcement Learning
                                                                          1. Cooperative Learning
                                                                            1. Competitive Learning
                                                                              1. Communication Protocols
                                                                              2. Applications of Deep Reinforcement Learning
                                                                                1. Game Playing
                                                                                  1. Atari Games
                                                                                    1. Board Games
                                                                                      1. Real-Time Strategy Games
                                                                                      2. Robotics
                                                                                        1. Manipulation Tasks
                                                                                          1. Locomotion
                                                                                          2. Autonomous Systems
                                                                                            1. Autonomous Driving
                                                                                              1. Drone Control
                                                                                              2. Resource Management
                                                                                                1. Trading and Finance

                                                                                              Previous

                                                                                              8. Generative Models

                                                                                              Go to top

                                                                                              Next

                                                                                              10. Advanced Topics and Specialized Architectures