Benchmarking Safe Deep Reinforcement Learning in Aquatic Navigation.
Enrico MarchesiniDavide CorsiAlessandro FarinelliPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- model free
- function approximation
- multi agent
- highly dynamic
- state space
- reinforcement learning algorithms
- temporal difference
- optimal policy
- indoor environments
- learning algorithm
- web navigation
- autonomous vehicles
- stochastic approximation
- robot navigation
- multi agent reinforcement learning
- supervised learning
- learning process
- multi agent systems
- genetic algorithm
- autonomous learning
- robotic control
- relational reinforcement learning
- temporal difference learning
- navigation systems
- real time
- markov decision process
- robot control
- partially observable
- learning capabilities
- information space
- learning problems
- markov decision processes
- transfer learning
- mobile robot
- machine learning