Reward function shape exploration in adversarial imitation learning: an empirical study.
Yawei WangXiu LiPublished in: CoRR (2021)
Keyphrases
- imitation learning
- reward function
- reinforcement learning
- reinforcement learning algorithms
- inverse reinforcement learning
- state space
- markov decision processes
- robotic systems
- maximum margin
- optimal policy
- multiple agents
- humanoid robot
- reinforcement learning methods
- state variables
- multi agent
- action selection
- machine learning
- random walk
- transition probabilities
- maximum likelihood