Optimizing Naval Movement Using Deep Reinforcement Learning.
Joseph CobleArmon BartonChristian DarkenScotty BlackPublished in: ICMLA (2023)
Keyphrases
- reinforcement learning
- state space
- united states
- reinforcement learning algorithms
- function approximation
- machine learning
- markov decision processes
- robotic control
- control problems
- exploration exploitation tradeoff
- temporal difference
- model free
- neural network
- learning process
- optimal control
- partially observable
- multi agent
- relational reinforcement learning
- trajectory data
- real time
- sufficient conditions
- fitted q iteration
- policy search
- air force
- transition model
- multi agent reinforcement learning
- temporal difference learning
- function approximators
- learning agent
- deep learning
- real robot
- dynamic programming
- action selection
- mobile robot