Hierarchical Reinforcement Learning (HRL)

Youtube search... ...Google search

• The Promise of Hierarchical Reinforcement Learning | Yannis Flet-Berliac - The Gradient
• Hierarchical Reinforcement Learning | David Jardim

• Reinforcement Learning (RL)
  • Monte Carlo (MC) Method - Model Free Reinforcement Learning
  • Markov Decision Process (MDP)
  • State-Action-Reward-State-Action (SARSA)
  • Q Learning
    • Deep Q Network (DQN)
  • Deep Reinforcement Learning (DRL) DeepRL
  • Distributed Deep Reinforcement Learning (DDRL)
  • Evolutionary Computation / Genetic Algorithms
  • Actor Critic
    • Asynchronous Advantage Actor Critic (A3C)
    • Advanced Actor Critic (A2C)
    • Lifelong Latent Actor-Critic (LILAC)
  • Hierarchical Reinforcement Learning (HRL)
• Policy ... Policy vs Plan ... Constitutional AI ... Trust Region Policy Optimization (TRPO) ... Policy Gradient (PG) ... Proximal Policy Optimization (PPO)

HRL is a promising approach to extend traditional Reinforcement Learning (RL) methods to solve more complex tasks.

HIerarchical Reinforcement learning with Off-policy correction (HIRO)

• Beyond DQN/A3C: A Survey in Advanced Reinforcement Learning | Joyce Xu - Towards Data Science
• Data-Efficient Hierarchical Reinforcement Learning | O. Nachum, S. Gu, H. Lee, and S. Levine - Google Brain

HIRO can be used to learn highly complex behaviors for simulated robots, such as pushing objects and utilizing them to reach target locations, learning from only a few million samples, equivalent to a few days of real-time interaction. In comparisons with a number of prior HRL methods.