Provable Benefits of Multi-task RL under Non-Markovian Decision Making Processes.
Ruiquan HuangYuan ChengJing YangVincent TanYingbin LiangPublished in: CoRR (2023)
Keyphrases
- multi task
- reinforcement learning
- decision making
- multi task learning
- transfer learning
- decision processes
- learning problems
- learning tasks
- multitask learning
- multiple tasks
- partially observable domains
- feature selection
- multi class
- gaussian processes
- decision process
- markov decision processes
- information gain
- sparse learning
- learning process
- data mining
- data sets
- high order
- prior knowledge