Imitating Cost-Constrained Behaviors in Reinforcement Learning.
Qian ShaoPradeep VarakanthamShih-Fen ChengPublished in: ICAPS (2024)
Keyphrases
- reinforcement learning
- state space
- function approximation
- total cost
- machine learning
- database
- supervised learning
- cost sensitive
- high cost
- reinforcement learning algorithms
- real robot
- autonomous learning
- cost reduction
- temporal difference learning
- cost savings
- behavior analysis
- communication cost
- markov decision processes
- multi agent
- real world
- neural network