A Survey of Meta-Reinforcement Learning.
Jacob BeckRisto VuorioEvan Zheran LiuZheng XiongLuisa M. ZintgrafChelsea FinnShimon WhitesonPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- reinforcement learning algorithms
- model free
- state space
- optimal policy
- machine learning
- temporal difference
- function approximation
- meta level
- multi agent
- direct policy search
- learning problems
- robot control
- learning agents
- reinforcement learning methods
- control problems
- high level abstraction
- perceptual aliasing
- meta reasoning
- relational reinforcement learning
- multi agent reinforcement learning
- temporal difference learning
- database
- reward function
- learning algorithm
- knowledge base
- learning classifier systems
- transfer learning