Obstacle Avoidance and Navigation Utilizing Reinforcement Learning with Reward Shaping.
Daniel ZhangColleen P. BaileyPublished in: CoRR (2020)
Keyphrases
- obstacle avoidance
- reward shaping
- reinforcement learning
- mobile robot
- path planning
- complex domains
- reinforcement learning algorithms
- autonomous vehicles
- visual navigation
- motion planning
- function approximation
- state space
- unknown environments
- learning algorithm
- agent learns
- markov decision problems
- model free
- markov decision processes
- optimal policy
- visually guided
- machine learning
- reward function
- temporal difference
- linear programming
- expert systems
- bayesian networks
- artificial intelligence