When to Trust Your Simulator: Dynamics-Aware Hybrid Offline-and-Online Reinforcement Learning.
Haoyi NiuShubham SharmaYiwen QiuMing LiGuyue ZhouJianming HuXianyuan ZhanPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- real time
- online learning
- website design
- function approximation
- trust model
- learning algorithm
- real robot
- dynamical systems
- simulation model
- hybrid learning
- trust evaluation
- policy search
- balancing exploration and exploitation
- internet commerce
- consumer trust
- online consumer
- cross cultural
- product reviews
- reinforcement learning algorithms
- model free
- markov decision processes
- cellular automata
- state space
- genetic algorithm