Pessimistic Value Iteration for Multi-Task Data Sharing in Offline Reinforcement Learning.
Chenjia BaiLingxiao WangJianye HaoZhuoran YangBin ZhaoZhen WangXuelong LiPublished in: CoRR (2024)
Keyphrases
- data sharing
- multi task
- reinforcement learning
- markov decision processes
- state space
- transfer learning
- learning problems
- multi task learning
- optimal policy
- learning tasks
- data access
- data integration
- multitask learning
- peer to peer
- information sharing
- multi class
- multiple tasks
- gaussian processes
- sparse learning
- learning algorithm
- feature selection
- machine learning
- supervised learning
- collaborative filtering
- information gain
- knowledge discovery
- learning process
- database systems
- elastic net