Provable Benefits of Multi-task RL under Non-Markovian Decision Making Processes.
Ruiquan HuangYuan ChengJing YangVincent TanYingbin LiangPublished in: ICLR (2024)
Keyphrases
- multi task
- decision making
- reinforcement learning
- transfer learning
- multi task learning
- decision processes
- learning tasks
- multitask learning
- learning problems
- decision process
- multi class
- multiple tasks
- gaussian processes
- sparse learning
- machine learning
- markov decision processes
- partially observable domains
- feature selection
- machine learning algorithms
- learning process
- learning algorithm
- optimal policy
- natural language processing
- data sets