Keyphrases
- multi task
- reinforcement learning
- long term
- transfer learning
- optimal policy
- learning problems
- reward function
- multi task learning
- learning tasks
- markov decision processes
- action selection
- state space
- multitask learning
- markov decision process
- markov decision problems
- control policy
- multi class
- reinforcement learning algorithms
- function approximators
- sparse learning
- partially observable markov decision processes
- multiple tasks
- feature selection
- average reward
- machine learning
- recommender systems
- learning algorithm
- gaussian processes
- agent learns
- supervised learning
- reward signal