Stabilising viscous extensional flows using Reinforcement Learning.
Marco VonaEric LaugaPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- mass transfer
- multi agent
- state space
- model free
- policy search
- optimal control
- supervised learning
- control problems
- temporal difference
- temporal difference learning
- stochastic approximation
- optimal policy
- direct policy search
- multi agent reinforcement learning
- relational reinforcement learning
- learning agents
- robotic control
- learning classifier systems
- action selection
- database
- partial order
- integrity constraints
- markov decision processes
- monte carlo
- search engine
- real world
- neural network