Hybrid of Reinforcement and Imitation Learning for Human-Like Agents.
Rousslan Fernand Julien DossaXinyu LianHirokazu NomotoTakashi MatsubaraKuniaki UeharaPublished in: IEICE Trans. Inf. Syst. (2020)
Keyphrases
- imitation learning
- reinforcement learning
- multi agent
- agent receives
- multi agent systems
- intelligent agents
- multiple agents
- single agent
- autonomous agents
- action selection
- robotic systems
- humanoid robot
- maximum margin
- reinforcement learning methods
- agent model
- dynamic environments
- relational domains
- concept learning
- model free
- computer vision
- markov decision processes
- optimal policy
- dynamic programming
- bayesian networks