Prioritizing Samples in Reinforcement Learning with Reducible Loss.
Shivakanth SujitSomjit NathPedro H. M. BragaSamira Ebrahimi KahouPublished in: NeurIPS (2023)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- multi agent
- robotic control
- machine learning
- action selection
- data sets
- model free
- training samples
- state space
- data samples
- learning problems
- sampling methods
- spectral data
- multi agent reinforcement learning
- markov decision processes
- image set
- supervised learning
- dynamic programming
- learning process
- feature selection
- learning algorithm
- neural network