Bayesian Design Principles for Offline-to-Online Reinforcement Learning.
Hao HuYiqin YangJianing YeChengjie WuZiqing MaiYujing HuTangjie LvChangjie FanQianchuan ZhaoChongjie ZhangPublished in: CoRR (2024)
Keyphrases
- design principles
- reinforcement learning
- instructional design
- design decisions
- software engineering
- real time
- online learning
- user interface
- function approximation
- design patterns
- design process
- state space
- serious games
- database
- bayesian networks
- case study
- learning algorithm
- databases
- multi agent
- optimal policy
- database design
- database systems
- e learning
- artificial intelligence
- interface design