Behaviour-conditioned policies for cooperative reinforcement learning tasks.
Antti KeurulainenIsak WesterlundAriel KwiatkowskiSamuel KaskiAlexander IlinPublished in: CoRR (2021)
Keyphrases
- learning tasks
- cooperative
- reinforcement learning
- learning problems
- transfer learning
- machine learning
- learning algorithm
- learning experience
- supervised learning
- meta learning
- reward function
- optimal policy
- multi task
- multitask learning
- function approximation
- learning models
- metric learning
- multi task learning
- machine learning algorithms
- hypothesis space
- kernel methods
- multi label
- similarity measure