Deep Reinforcement Learning for Feedback Control in a Collective Flashing Ratchet.
Dong-Kyum KimHawoong JeongPublished in: CoRR (2020)
Keyphrases
- feedback control
- reinforcement learning
- optimal control
- adaptive control
- closed loop
- adaptive fuzzy
- fractional order
- open loop
- function approximation
- collective intelligence
- dynamic programming
- optimal policy
- autonomous control
- inverted pendulum
- state space
- linear time invariant
- reinforcement learning algorithms
- temporal difference
- markov decision processes
- action selection
- learning algorithm
- machine learning
- nonlinear systems
- control law
- multi agent
- networked control systems