Delayed Reinforcement Learning by Imitation.
Pierre LiotetDavide MaranLorenzo BisiMarcello RestelliPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- imitation learning
- state space
- function approximation
- machine learning
- reinforcement learning algorithms
- markov decision processes
- control problems
- multi agent
- model free
- robotic control
- learning algorithm
- learning problems
- dynamic programming
- evolutionary algorithm
- temporal difference
- learning process
- dynamic environments
- optimal policy
- transfer learning
- supervised learning
- optimal control
- partially observable
- learning agents
- information retrieval
- real time