Improvements to Vanilla Implementation of Q-Learning Used in Path Planning of an Agent.
Aritra BhuiyaSuresh Chandra SatapathyPublished in: FICTA (2) (2021)
Keyphrases
- path planning
- potential field
- dynamic environments
- multi agent
- mobile robot
- path planning algorithm
- obstacle avoidance
- multi robot
- collision avoidance
- action selection
- indoor environments
- multi agent systems
- dynamic and uncertain environments
- single agent
- reinforcement learning
- multiple robots
- motion planning
- optimal path
- decision making
- autonomous navigation
- learning agent
- intelligent agents
- autonomous vehicles
- multiagent systems
- navigation tasks
- autonomous agents
- path finding
- search space
- robot path planning
- collision free
- agent model
- trajectory planning
- aerial vehicles
- path planner
- degrees of freedom
- uncertain environments
- search algorithm
- search and rescue
- configuration space
- dynamic programming