TACO: Learning Task Decomposition via Temporal Alignment for Control.
Kyriacos ShiarlisMarkus WulfmeierSasha SalterShimon WhitesonIngmar PosnerPublished in: ICML (2018)
Keyphrases
- learning systems
- learning algorithm
- learning process
- knowledge acquisition
- social networks
- inductive learning
- online learning
- supervised learning
- control rules
- learning scheme
- learning community
- learning tasks
- unsupervised learning
- data sets
- probabilistic model
- reinforcement learning
- case study
- real world
- neural network