On Reward Shaping for Mobile Robot Navigation: A Reinforcement Learning and SLAM Based Approach.
Nicolò BotteghiBeril SirmaçekKhaled A. A. MustafaMannes PoelStefano StramigioliPublished in: CoRR (2020)
Keyphrases
- mobile robot navigation
- reward shaping
- mobile robot
- reinforcement learning
- vision guided
- unknown environments
- reinforcement learning algorithms
- complex domains
- simultaneous localization and mapping
- mobile robotics
- agent learns
- obstacle avoidance
- indoor environments
- state space
- path planning
- function approximation
- markov decision processes
- topological map
- model free
- markov decision problems
- reward function
- autonomous navigation
- robotic systems
- dynamic environments
- autonomous robots
- outdoor environments
- multi robot
- optimal control
- optimal policy
- dynamic programming
- policy search
- learning algorithm
- temporal difference
- image interpretation
- learning process
- real robot
- action selection
- domain theory
- motion planning
- particle filter
- multi agent
- machine learning