Multi-Task Reinforcement Learning as a Hidden-Parameter Block MDP.
Amy ZhangShagun SodhaniKhimya KhetarpalJoelle PineauPublished in: CoRR (2020)
Keyphrases
- multi task
- reinforcement learning
- transfer learning
- markov decision processes
- learning problems
- multi task learning
- markov decision process
- learning tasks
- optimal policy
- state space
- multitask learning
- multiple tasks
- reward function
- multi class
- feature selection
- sparse learning
- learning algorithm
- action space
- gaussian processes
- supervised learning
- machine learning
- dynamic programming
- learning process
- feature extraction
- image segmentation
- data mining
- data sets