Deep-Reinforcement-Learning for Gliding and Perching Bodies.
Guido NovatiLakshminarayanan MahadevanPetros KoumoutsakosPublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- function approximation
- model free
- markov decision processes
- machine learning
- robotic control
- learning algorithm
- control problems
- temporal difference
- state space
- dynamic programming
- learning problems
- optimal control
- temporal difference learning
- transition model
- optimal policy
- supervised learning
- search algorithm
- reward function
- multiscale
- multi agent reinforcement learning
- artificial intelligence