Skip to main content

Table 1 The comparison of the most representation reinforcement learning algorithms

From: Adversarial attack and defense in reinforcement learning-from AI security view

RL algorithm Approach type Learning type Application scenarios
Q-Learning (Watkins and Dayan 1992) Value-based Shallow Learning Motion Control, Control System,
    and Robot Application et al.
DQN (Mnih et al. 2013) Value-based Deep Learning Motion Control, Neutralization Reaction
    Control, and Robot Path Planning et al.
VIN (Tamar et al. 2016) Value-based Deep Learning Path Planning, and Motion Control et al.
A3C (Mnih et al. 2016) Combined Deep Learning motion Control, Game Playing, self-driving,
    and Path Planning et al.
TRPO (Schulman et al. 2015) Policy-based Deep Learning Motion Control, and Game Playing et al.
UNREAL (Jaderberg et al. 2016) Combined Deep Learning Motion Control, and Game Playing et al.
  1. Approach Type contains two categories, namely Policy-based, and Value-based. Meanwhile, learning Type also contains two categories, namely Shallow Learning, and Deep Learning