Benchmarking Safe Deep Reinforcement Learning in Aquatic Navigation.
Enrico MarchesiniDavide CorsiAlessandro FarinelliPublished in: IROS (2021)
Keyphrases
- reinforcement learning
- function approximation
- highly dynamic
- state space
- navigation systems
- optimal control
- machine learning
- reinforcement learning algorithms
- temporal difference
- robotic control
- outdoor environments
- web navigation
- optimal policy
- robot navigation
- information space
- dynamic programming
- deep learning
- relational reinforcement learning
- route planning
- land vehicle
- action space
- autonomous vehicles
- markov decision process
- learning classifier systems
- indoor environments
- markov decision processes
- transfer learning
- supervised learning
- multi agent
- learning algorithm