SplAgger: Split Aggregation for Meta-Reinforcement Learning.
Jacob BeckMatthew Thomas JacksonRisto VuorioZheng XiongShimon WhitesonPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- function approximation
- data aggregation
- model free
- reinforcement learning algorithms
- meta level
- state space
- action space
- direct policy search
- dynamic programming
- transfer learning
- domain knowledge
- machine learning
- control problems
- aggregation operators
- rank aggregation
- learning problems
- active learning
- temporal difference
- learning environment
- multi agent
- learning agent