Bridging Imitation and Online Reinforcement Learning: An Optimistic Tale.
Botao HaoRahul JainDengwang TangZheng WenPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- function approximation
- balancing exploration and exploitation
- state space
- real time
- markov decision processes
- model free
- reinforcement learning algorithms
- multi agent
- online learning
- learning algorithm
- temporal difference
- transfer learning
- control policy
- function approximators
- optimal control
- evaluation function
- dynamic programming
- social networks
- genetic algorithm
- machine learning
- neural network