SWiMM DEEPeR: A Simulated Underwater Environment for Tracking Marine Mammals Using Deep Reinforcement Learning and BlueROV2.
Samuel ApplebyKirsten CraneGiacomo BergamiA. Stephen McGoughPublished in: CoG (2023)
Keyphrases
- reinforcement learning
- real robot
- real time
- test bed
- controlled environment
- function approximation
- simulated robot
- dynamic environments
- target tracking
- neural network
- robust tracking
- particle filter
- mobile robot
- appearance model
- kalman filter
- optimal control
- mean shift
- reinforcement learning algorithms
- optimal policy
- state space
- multi agent environments