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