DRIFT: Deep Reinforcement Learning for Intelligent Floating Platforms Trajectories.
Matteo El HariryAntoine RichardVivek MuralidharanBaris Can YalçinMatthieu GeistMiguel A. Olivares-MéndezPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- learning capabilities
- trajectory data
- reinforcement learning algorithms
- function approximation
- state space
- moving objects
- markov decision processes
- multi agent
- intelligent systems
- optimal policy
- moving object trajectories
- model free
- neural network
- multi agent reinforcement learning
- spatio temporal
- learning algorithm
- machine learning
- decision support
- dynamic programming
- concept drift
- temporal difference
- expert systems
- artificial intelligence
- trajectories of moving objects
- data sets
- robotic control