Jet grooming through reinforcement learning.
Stefano CarrazzaFrédéric A. DreyerPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- function approximation
- model free
- markov decision processes
- reinforcement learning algorithms
- scale invariant
- optimal policy
- state space
- direct policy search
- dynamic programming
- learning process
- robotic control
- relational reinforcement learning
- fluid flow
- learning algorithm
- learning agents
- flow field
- neural network
- action selection
- database
- website
- reinforcement learning methods
- temporal difference learning
- real time
- temporal difference
- data sets
- learning classifier systems
- machine learning
- learning problems
- genetic algorithm
- sufficient conditions
- markov chain
- information systems
- decision making
- multi agent