A Deep Reinforcement Learning Approach to Configuration Sampling Problem.
Amir AbolfazliJakob SpiegelbergGregory PalmerAvishek AnandPublished in: ICDM (2023)
Keyphrases
- reinforcement learning
- function approximation
- temporal difference
- random sampling
- robotic control
- sampling strategy
- state space
- reinforcement learning algorithms
- monte carlo
- model free
- markov decision processes
- neural network
- sampling strategies
- multi agent reinforcement learning
- learning capabilities
- action selection
- optimal control
- parameter space
- markov chain monte carlo
- transfer learning
- sample size
- markov chain
- supervised learning
- support vector machine
- learning process
- stochastic approximation
- genetic algorithm
- machine learning
- real time