FedFormer: Contextual Federation with Attention in Reinforcement Learning.
Liam HebertLukasz GolabPascal PoupartRobin CohenPublished in: AAMAS (2023)
Keyphrases
- reinforcement learning
- contextual information
- state space
- function approximation
- learning algorithm
- multi agent
- context sensitive
- real time
- databases
- reinforcement learning algorithms
- decision making
- heterogeneous database systems
- temporal difference learning
- robot control
- context dependent
- optimal control
- visual attention
- mobile agents
- optimal policy
- control system
- artificial intelligence
- machine learning
- data mining
- data sets