Rapid locomotion via reinforcement learning.
Gabriel B. MargolisGe YangKartik PaigwarTao ChenPulkit AgrawalPublished in: Int. J. Robotics Res. (2024)
Keyphrases
- reinforcement learning
- robot control
- function approximation
- reinforcement learning algorithms
- control problems
- state space
- markov decision processes
- degrees of freedom
- temporal difference
- model free
- mobile robot
- optimal policy
- robotic systems
- direct policy search
- temporal difference learning
- optimal control
- transfer learning
- learning algorithm
- pose estimation
- sufficient conditions
- action selection
- learning process
- multi agent
- genetic algorithm
- action space
- machine learning
- multi agent reinforcement learning
- policy search
- rough terrain
- relational reinforcement learning
- real world