Deep reinforcement learning using compositional representations for performing instructions.
Mohammad-Ali ZamaniSven MaggCornelius WeberStefan WermterDi FuPublished in: Paladyn J. Behav. Robotics (2018)
Keyphrases
- reinforcement learning
- function approximation
- state space
- multi agent
- higher level
- deep learning
- reinforcement learning algorithms
- supervised learning
- autonomous learning
- database
- function approximators
- symbolic representation
- markov decision processes
- unsupervised learning
- high level
- learning algorithm
- machine learning
- data sets
- real time