Scaling Learning based Policy Optimization for Temporal Tasks via Dropout.
Navid HashemiBardh HoxhaDanil V. ProkhorovGeorgios FainekosJyotirmoy DeshmukhPublished in: CoRR (2024)
Keyphrases
- learning systems
- multiple tasks
- learning process
- multi task
- active learning
- multi task learning
- autonomous robots
- learning tasks
- optimization algorithm
- global optimization
- spatial and temporal
- knowledge acquisition
- online learning
- supervised learning
- prior knowledge
- reinforcement learning
- neural network
- unsupervised learning
- optimization method
- learning analytics
- temporal reasoning
- decision trees
- learning algorithm