Discounted Markov Decision Processes with Fuzzy Rewards Induced by Non-fuzzy Systems.
Karla Carrero-VeraHugo Cruz-SuárezRaúl Montes-de-OcaPublished in: ICORES (2021)
Keyphrases
- markov decision processes
- fuzzy systems
- fuzzy rules
- soft computing
- evolutionary computation
- takagi sugeno
- neural network
- reinforcement learning
- computational intelligence
- optimal policy
- rule base
- state space
- finite state
- neural fuzzy
- average cost
- fuzzy model
- average reward
- infinite horizon
- policy iteration
- transition matrices
- reward function
- fuzzy logic
- markov decision process
- dynamic programming
- finite horizon
- artificial neural networks
- reinforcement learning algorithms
- fuzzy partition
- membership functions
- fuzzy rule based systems
- partially observable
- total reward
- discounted reward
- fuzzy inference system
- fuzzy controller
- t norm
- fuzzy sets
- artificial intelligence
- decision theoretic planning
- state and action spaces
- evolutionary algorithm
- expected reward
- decision making
- fuzzy control