MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning.
Kevin LiAbhishek GuptaAshwin ReddyVitchyr PongAurick ZhouJustin YuSergey LevinePublished in: CoRR (2021)
Keyphrases
- meta learning
- reinforcement learning
- learning tasks
- inductive learning
- machine learning
- meta knowledge
- model selection
- markov decision processes
- machine learning algorithms
- transfer learning
- state space
- decision trees
- learning algorithm
- supervised learning
- feature selection
- data mining
- reward function
- base classifiers
- optimal policy
- case study
- data sets
- multi agent
- naive bayes
- semi supervised learning
- pairwise