Keyphrases
- actor critic
- potential field
- reinforcement learning
- dynamic environments
- temporal difference
- reinforcement learning algorithms
- path planning
- biologically inspired
- policy gradient
- approximate dynamic programming
- mobile robot
- optimal control
- neuro fuzzy
- gradient method
- function approximation
- force field
- multi robot
- obstacle avoidance
- policy iteration
- state space
- motion planning
- model free
- unknown environments
- collision avoidance
- optimal policy
- markov decision processes
- learning algorithm
- rl algorithms
- multi agent
- function approximators
- collision free
- temporal difference learning
- machine learning
- dynamical systems