Accelerated Policy Learning with Parallel Differentiable Simulation.
Jie XuViktor MakoviychukYashraj S. NarangFabio T. RamosWojciech MatusikAnimesh GargMiles MacklinPublished in: CoRR (2022)
Keyphrases
- learning algorithm
- online learning
- reinforcement learning
- unsupervised learning
- learning process
- active learning
- action selection
- parallel processing
- learning problems
- learning tasks
- learning systems
- genetic algorithm
- machine learning
- prior knowledge
- pairwise
- decision making
- background knowledge
- data sets
- learning analytics
- inductive inference
- real time