Online No-regret Model-Based Meta RL for Personalized Navigation.
Yuda SongYe YuanWen SunKris KitaniPublished in: L4DC (2022)
Keyphrases
- online learning
- reinforcement learning
- model free
- e learning
- lower bound
- online algorithms
- real time
- online convex optimization
- online video
- worst case
- state space
- markov decision processes
- autonomous learning
- batch mode
- robot navigation
- indoor environments
- function approximation
- game theory
- user profiles
- least squares
- multi agent
- social networks