Managing engineering systems with large state and action spaces through deep reinforcement learning.
C. P. AndriotisK. G. PapakonstantinouPublished in: CoRR (2018)
Keyphrases
- state and action spaces
- engineering systems
- reinforcement learning
- markov decision processes
- action space
- computational intelligence
- engineering problems
- state space
- average reward
- markov decision problems
- partially observable markov decision process
- real valued
- function approximation
- dynamic programming
- temporal difference
- data mining
- expert systems
- decision processes
- action selection
- evolutionary computation
- supervised learning
- fuzzy logic