Decentralized Deep Reinforcement Learning for a Distributed and Adaptive Locomotion Controller of a Hexapod Robot.
Malte SchillingKai KonenFrank W. OhlTimo KorthalsPublished in: IROS (2020)
Keyphrases
- legged robots
- reinforcement learning
- multi agent
- distributed systems
- central pattern generator
- mobile robot
- real robot
- quadruped robot
- robot control
- peer to peer
- cooperative
- inverted pendulum
- robotic systems
- adaptive control
- motion control
- legged locomotion
- rough terrain
- distributed agents
- control architecture
- real time
- function approximation
- distributed constraint optimization
- actor critic
- feedback control
- autonomous robots
- reinforcement learning algorithms
- modular robots
- contact force
- temporal difference
- multi robot
- robot moves
- biped walking
- dynamic programming
- learning algorithm