Distributional reinforcement learning with unconstrained monotonic neural networks.
Thibaut ThéateAntoine WehenkelAdrien BollandGilles LouppeDamien ErnstPublished in: Neurocomputing (2023)
Keyphrases
- neural network
- reinforcement learning
- function approximators
- pattern recognition
- co occurrence
- state space
- function approximation
- multi layer
- reinforcement learning algorithms
- model free
- learning capabilities
- artificial neural networks
- back propagation
- markov decision processes
- learning algorithm
- temporal difference
- machine learning
- learning classifier systems
- fuzzy systems
- neural nets
- self organizing maps
- fault diagnosis
- fuzzy logic
- recurrent neural networks
- neural network model
- learning problems
- optimal policy
- genetic algorithm
- robotic control
- feed forward
- expert systems
- multi agent
- training data
- hopfield neural network
- adaptive resonance theory