Learning Long-Term Reward Redistribution via Randomized Return Decomposition.
Zhizhou RenRuihan GuoYuan ZhouJian PengPublished in: CoRR (2021)
Keyphrases
- long term
- reinforcement learning
- learning process
- short term
- learning algorithm
- supervised learning
- neural network
- online learning
- background knowledge
- database
- active learning
- artificial neural networks
- learning systems
- machine learning
- mobile learning
- data mining
- learning tasks
- incremental learning
- inductive learning
- learning community
- inductive inference
- eligibility traces