Learning from Suboptimal Demonstration via Self-Supervised Reward Regression.
Letian ChenRohan R. PalejaMatthew C. GombolayPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- learning algorithm
- learning systems
- incremental learning
- learning process
- online learning
- knowledge acquisition
- prior knowledge
- active learning
- unsupervised learning
- classification and regression problems
- locally weighted
- solving problems
- inductive inference
- learning scheme
- linear regression
- learning tasks
- model selection
- bayesian networks