Controllers and agents

Jump to bottom

BorjaFG edited this page Feb 27, 2019 · 2 revisions

RLSimion features the following controllers and agents:

Regular controllers
- Proportional-Integrative-Derivative (PID)
- Linear-Quadratic Regulator (LQR)
- Variable-Speed Wind-Turbine controllers
  - Jonkman
  - Boukhezzar
  - Vidal[#Fernandez-Gauna2017]
Linear VFA-based Q-function algorithms
- SARSA
- Q-Learning
- Double Q-Learning
Actor-Critic algorithms
- CACLA
- Regular gradient ascent
- Incremental Natural Actor-Critic
- Off-Policy Actor-Critic
- Off-Policy Deterministic Actor-Critic
- Besides, actors can be combined with Value function learning critics:
  - Temporal-Difference (lambda)
  - TDC(lambda)
  - True Online Temporal-Difference.
Deep RL methods
- DQN
- Double-DQN
- DDPG

SimionSoft - Group of Computational Intelligence ( University of the Basque Country (UPV/EHU) )