Reinforcement learning of path-finding behaviour by a mobile robot.
Kurt MalmstromL. MundayJoaquin SittePublished in: ANZIIS (1996)
Keyphrases
- path finding
- mobile robot
- path planning
- reinforcement learning
- real robot
- obstacle avoidance
- collision avoidance
- optimal path
- heuristic search
- dynamic environments
- search algorithm
- state space
- reward function
- hill climbing
- dynamic programming
- learning algorithm
- neural network
- data mining techniques
- multi agent
- data mining