A Deep Safe Reinforcement Learning Approach for Mapless Navigation.
Shaohua LvYanjie LiQi LiuJianqi GaoXizheng PangMeiling ChenPublished in: ROBIO (2021)
Keyphrases
- reinforcement learning
- function approximation
- learning algorithm
- reinforcement learning algorithms
- temporal difference learning
- temporal difference
- state space
- outdoor environments
- markov decision processes
- navigation systems
- action selection
- relational reinforcement learning
- indoor environments
- optimal policy
- mobile robot
- learning process
- machine learning
- robotic control
- structured environments
- multi agent reinforcement learning
- web navigation
- belief nets
- real time
- function approximators
- autonomous vehicles
- obstacle avoidance
- information space
- dynamic programming
- multi agent
- data mining