Modelling Agent Policies with Interpretable Imitation Learning.
Tom BewleyJonathan LawryArthur RichardsPublished in: CoRR (2020)
Keyphrases
- imitation learning
- reinforcement learning
- reward function
- multi agent
- maximum margin
- multi agent systems
- robotic systems
- optimal policy
- humanoid robot
- multiple agents
- markov decision process
- machine learning
- dynamic environments
- human teacher
- action selection
- model construction
- agent model
- state space
- markov decision processes
- computer vision