Option Compatible Reward Inverse Reinforcement Learning.
Rakhoon HwangHanjin LeeHyung Ju HwangPublished in: CoRR (2019)
Keyphrases
- finite horizon
- inverse reinforcement learning
- optimal policy
- reward function
- partially observable environments
- bayesian nonparametric
- preference elicitation
- reinforcement learning
- reinforcement learning algorithms
- state space
- decision problems
- artificial intelligence
- multi objective
- personal information
- finite state