Modelling Agent Policies with Interpretable Imitation Learning.
Tom BewleyJonathan LawryArthur RichardsPublished in: TAILOR (2020)
Keyphrases
- imitation learning
- reinforcement learning
- multi agent systems
- multi agent
- reward function
- optimal policy
- humanoid robot
- markov decision process
- human teacher
- robotic systems
- action selection
- maximum margin
- agent model
- multiple agents
- state space
- learning algorithm
- single agent
- function approximation
- learning agent
- image sequences