When to Trust Your Simulator: Dynamics-Aware Hybrid Offline-and-Online Reinforcement Learning.
Haoyi NiuShubham SharmaYiwen QiuMing LiGuyue ZhouJianming HuXianyuan ZhanPublished in: NeurIPS (2022)
Keyphrases
- reinforcement learning
- real time
- online learning
- website design
- function approximation
- consumer trust
- learning algorithm
- state space
- dynamical systems
- dynamic model
- reputation management
- real robot
- trust model
- virtual communities
- simulation model
- learning classifier systems
- hybrid learning
- optimal policy
- learning process
- search engine
- trust propagation
- neural network