Inverse Reinforcement Learning with Locally Consistent Reward Functions.
Quoc Phong NguyenKian Hsiang LowPatrick JailletPublished in: NIPS (2015)
Keyphrases
- inverse reinforcement learning
- reward function
- preference elicitation
- markov decision processes
- reinforcement learning
- state space
- optimal policy
- reinforcement learning algorithms
- partially observable
- simple examples
- multiple agents
- transition probabilities
- markov decision process
- dynamic systems
- function approximation
- infinite horizon