Developmentally Synthesizing Earthworm-Like Locomotion Gaits with Bayesian-Augmented Deep Deterministic Policy Gradients (DDPG).
Sayyed Jaffar Ali RazaApan DastiderMingjie LinPublished in: CASE (2020)
Keyphrases
- legged robots
- quadruped robot
- belief nets
- robotic systems
- fluid model
- optimal policy
- rough terrain
- inverted pendulum
- bayesian networks
- degrees of freedom
- bayesian inference
- bayesian learning
- image gradient
- fully observable
- sagittal plane
- mobile robot
- dynamic programming
- control policies
- mechanical systems
- inverse reinforcement learning
- monte carlo sampling
- control policy
- maximum likelihood
- probability distribution