Learning to Control Autonomous Fleets from Observation via Offline Reinforcement Learning.
Carolin SchmidtDaniele GammelliFrancisco Câmara PereiraFilipe RodriguesPublished in: ECC (2024)
Keyphrases
- reinforcement learning
- learning algorithm
- learning process
- learning capabilities
- autonomous learning
- learning problems
- learning tasks
- online learning
- supervised learning
- adaptive control
- prior knowledge
- control problems
- robot control
- control system
- optimal control
- control method
- multi agent
- continuous state
- temporal difference learning
- autonomous systems
- autonomous robots
- function approximation
- active learning
- markov decision processes