Sim-to-Real Learning of All Common Bipedal Gaits via Periodic Reward Composition.

Jonah Siekmann Yesh Godse Alan Fern Jonathan W. Hurst

Published in: ICRA (2021)

Keyphrases

reinforcement learning
learning algorithm
learning process
online learning
learning problems
supervised learning
active learning
autonomous robots
knowledge acquisition
learning systems
learning tasks
mobile learning
eligibility traces
data sets
background knowledge
semi supervised
state space
real world