Particle swarm optimization for generating interpretable fuzzy reinforcement learning policies.
Daniel HeinAlexander HentschelThomas A. RunklerSteffen UdluftPublished in: Eng. Appl. Artif. Intell. (2017)
Keyphrases
- particle swarm optimization
- reinforcement learning
- optimal policy
- pso algorithm
- fuzzy logic
- fuzzy sets
- policy search
- control policies
- membership functions
- function approximation
- markov decision process
- fuzzy rules
- state space
- multi objective
- reward function
- fuzzy neural network
- particle swarm optimization algorithm
- control policy
- markov decision processes
- global optimization
- fuzzy clustering
- temporal difference
- markov decision problems
- hierarchical reinforcement learning
- differential evolution
- reinforcement learning agents
- partially observable
- learning algorithm
- fitted q iteration
- fuzzy set theory
- multi agent
- swarm intelligence
- fuzzy numbers
- fuzzy systems
- model free
- partially observable markov decision processes
- fuzzy measures
- inertia weight
- convergence speed
- neuro fuzzy
- continuous state
- multi agent reinforcement learning
- multiagent reinforcement learning
- particle swarm optimization pso
- classification rules
- action selection