Robotics & Perception/Reinforcement Learning

Reinforcement learning 기억 되새기기

https://chatgpt.com/share/67b31115-6508-800d-8ada-662b2fed132e

  1. Basics
    1. Monte-Carlo, Temporal Difference
  2. Extensions
    1. Policy Optimization
      • Soft Actor Critic
    2. Q-learning
      1. Double Q-learning
      2. Overestimation issue 피하기 --IQL
    3. Interpolating Between Policy Optimization and Q-Learning.
      1. Soft Actor-Critic
      2. DDPG
저작자표시 비영리 동일조건

'Robotics & Perception > Reinforcement Learning' 카테고리의 다른 글

[Advanced Topics] 02. Representation Learning for RL  (0) 2023.09.16
[Advanced Topics] 01. RL with human feedback  (0) 2023.09.16
Proximal Policy Optimization Algorithms (PPO) Hyper-parameters  (0) 2022.05.15
[Policy Gradient] Vanilla Policy Gradient, Trust region policy optimization (TRPO), Proximal Policy Optimization Algorithms (PPO)  (0) 2022.05.11
[David Silver] 7. Policy Gradient: REINFORCE, Actor-Critic, NPG  (0) 2022.04.10
    Jisu_Han
    Jisu_Han

    티스토리툴바