Comparison of Deep Q-Learning, Q-Learning and SARSA Reinforced Learning for Robot Local Navigation.
Hafiq AnasWee-Hong OngOwais Ahmed MalikPublished in: RiTA (2021)
Keyphrases
- reinforcement learning
- learning algorithm
- function approximation
- temporal difference learning
- action selection
- cooperative
- potential field
- learning agent
- reinforcement learning algorithms
- learning tasks
- learning problems
- model free
- state space
- supervised learning
- learning process
- multi agent
- td learning
- learning rate
- simulated robot
- multi agent reinforcement learning
- reinforcement learning methods
- optimal policy
- eligibility traces
- autonomous learning
- temporal difference methods
- single agent
- rl algorithms
- function approximators
- deep learning
- robot control
- neural network
- multi robot
- evaluation function
- mobile robot