Login / Signup
Recurrent Network-based Deterministic Policy Gradient for Solving Bipedal Walking Challenge on Rugged Terrains.
Doo Re Song
Chuanyu Yang
Christopher McGreavy
Zhibin Li
Published in:
CoRR (2017)
Keyphrases
</>
policy gradient
parametric optimization
optimal control
neural network
reinforcement learning
function approximation
solving problems
multi agent
mathematical model
exact solution
reinforcement learning algorithms
actor critic
model free reinforcement learning