Towards Continual Reinforcement Learning for Quadruped Robots.
Giovanni MinelliVassilis VassiliadesPublished in: IMET (2023)
Keyphrases
- reinforcement learning
- quadruped robot
- legged robots
- real robot
- robotic control
- robot control
- mobile robot
- function approximation
- imitation learning
- state space
- cooperative
- multi robot
- markov decision processes
- robot behavior
- rough terrain
- temporal difference
- action selection
- multiple robots
- humanoid robot
- tactile sensing
- multi agent
- reinforcement learning algorithms
- reinforcement learning methods
- human robot interaction
- learning algorithm
- human robot
- robot soccer
- robotic systems
- optimal control
- transfer learning
- optimal policy
- policy search
- dynamic programming
- neural network
- autonomous robots
- machine learning
- inverted pendulum
- autonomous systems
- temporal difference learning
- path planning
- search and rescue
- multi robot systems
- model free