Learning Relative Return Policies With Upside-Down Reinforcement Learning.
Dylan R. AshleyKai ArulkumaranJürgen SchmidhuberRupesh Kumar SrivastavaPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- learning process
- learning algorithm
- optimal policy
- learning problems
- supervised learning
- learning systems
- prior knowledge
- online learning
- action selection
- eligibility traces
- knowledge acquisition
- reinforcement learning algorithms
- robot control
- learning agent
- reinforcement learning methods
- hierarchical reinforcement learning
- macro actions