Please enable JavaScript.

Coggle requires JavaScript to display documents.

Reinforcement Learning (Non Model Based (S,A,P?,R?,r?) (Temporal…

- - - - Path Integral Approach
      - Statistics Learning
      - Actor-Critic (A2C)
        
        A3C
        
        UNREAL
      - Policy Gradient
        
        PGQL #
        
        TRPO
        
        PPO2
        
        PPO(off-policy)
        
        DPPO
    - - DPG
        
        DDPG
        
        MADDPG
  - - - Sarsa(λ)
- - - - 2013 Guided Policy Search(GPS)
- - - - Guass
      - Legendre
      - Radau
      - Chebyshev
  - - - Can't solve Constrained Problem
- - - - Reinforcement Learning
        
        Experience Replay
        
        Deep NN approximate Value Function
        
        Target Network for TD bias
      - Double DQN
      - Prioritized Replay Double DQN
      - Dueling DQN
      - Imitation Learning
- - - - Structured Classification,
      - Neural RL
      - Apprenticeship Learning
      - MMP
    - - Maximum Entropy
      - Deep RL
      - Relative entropy