Hands on RL

• DQN
  • Overview
  • Quick Facts
  • Key Equations or Key Graphs
  • Pseudo-code
  • Extensions
  • Implementations
  • Reference
• C51
  • Overview
  • Quick Facts
  • Pseudo-code
  • Key Equations or Key Graphs
  • Extensions
  • Implementation
• QRDQN
  • Overview
  • Quick Facts
  • Key Equations or Key Graphs
  • Pseudo-code
  • Extensions
  • Implementation
• IQN
  • Overview
  • Quick Facts
  • Key Equations
  • Key Graphs
  • Extensions
  • Implementation
  • References
• Rainbow
  • Overview
  • Quick Facts
  • Double Q-learning
  • Prioritized Experience Replay(PER)
  • Dueling Network
  • Multi-step Learning
  • Noisy Net
  • Extensions
  • Implementation
  • Experiments on Rainbow Tricks
  • References
• SQN
  • Overview
  • Quick Facts
  • Key Equations or Key Graphs
  • Pseudocode
  • Extensions
  • Implementation
  • Other Public Implementations
• SQIL
  • Overview
  • Quick Facts
  • Key Equations or Key Graphs
  • Pseudo-code
  • Implementations
  • References
• A2C
  • Overview
  • Quick Facts
  • Key Equations or Key Graphs
  • Pseudo-code
  • Extensions
  • Implementation
  • References
• ACER
  • Overview
  • Quick Facts
  • Key Equations
    • Retrace Q-value estimation
    • policy gradient
  • Pseudocode
  • Implementations
  • Reference
• PPO
  • Overview
  • Quick Facts
  • Key Equations or Key Graphs
  • Pseudo-code
  • Extensions
  • Implementation
  • References
• PPG
  • Overview
  • Quick Facts
  • Key Graphs
  • Key Equations
  • Pseudo-code
  • Extensions
  • Implementation
  • References
• IMPALA
  • Overview
  • Quick Facts
  • Key Equations
  • Key Graphs
  • Implementations
  • Reference
• DDPG
  • Overview
  • Quick Facts
  • Key Equations or Key Graphs
  • Pseudocode
  • Extensions
  • Implementations
    • Model
    • Train actor-critic model
    • Target Network
  • Other Public Implementations
  • References
• TD3
  • Overview
  • Quick Facts
  • Key Equations or Key Graphs
  • Pseudocode
  • Extensions
  • Implementations
    • Model
    • Train actor-critic model
    • Target Network
    • Target Policy Smoothing Regularization
  • Other Public Implementations
  • References
• SAC
  • Overview
  • Quick Facts
  • Key Equations or Key Graphs
  • Pseudocode
  • Extensions
  • Implementation
  • Other Public Implementations
• QMIX
  • Overview
  • Quick Facts
  • Key Equations or Key Graphs
  • Extensions
  • Implementations
  • References
• COMA
  • Overview
  • Quick Facts
  • Key Equations or Key Graphs
  • Extensions
  • Implementations
  • References
• ATOC
  • Overview
  • Quick Facts
  • Key Equations or Key Graphs
  • Extensions
  • Implementations
  • References
• CollaQ
  • Overview
  • Quick Facts
  • Key Equations or Key Graphs
  • Extensions
  • Implementations
  • References
• RND
  • Overview
  • Quick Facts
  • Key Equations or Key Graphs
    • The implementation details that matters
  • Pseudo-Code
  • Code Implementation
    • RndNetwork
    • RndRewardModel
    • Train RndRewardModel
    • Calculate RND Reward
  • Benchmark Results
  • Author’s Tensorflow Implementation
  • Reference
• GAIL
  • Overview
  • Quick Facts
  • Key Equations or Key Graphs
  • Pseudo-Code
  • Extensions
  • Reference
• VPN
  • Overview
  • Quick Facts
  • Key Equations or Key Graphs
  • Pseudo-code
  • Extensions
  • Implementations
  • Reference
• MCTS
  • Overview
  • Quick Facts
  • Key Equations or Key Graphs
  • Pseudo-code
  • Extensions
  • Implementations
  • References
• AlphaGo
  • Overview
  • Quick-Facts
  • Key Equations or Key Graphs
  • Pseudo-code
  • Extensions
  • Implementations
• AlphaGoZero
  • Overview
  • Quick-Facts
  • Key Equations or Key Graphs
  • Pseudo-code
  • Extensions
  • Implementations
  • References