Fast and Stable Learning of Quasi-Passive Dynamic Walking by an Unstable Biped Robot based on Off-Policy Natural Actor-Critic

No abstract is available for this paper.

• Publication year

  2006

• Venue

  2006 IEEE/RSJ International Conference on Intelligent Robots and Systems

• Publication date

  2006-10-01

• Fields of study

  Computer Science, Engineering

• Identifiers
  DOI 10.1109/IROS.2006.281663
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Design and Construction of MIKE; a 2-D Autonomous Biped Based on Passive Dynamic Walking

  2006cited by this paper
• Efficient Bipedal Robots Based on Passive-Dynamic Walkers

  2005cited by this paper
• Ground Reference Points in Legged Locomotion: Definitions, Biological Trajectories and Control Implications

  2005cited by this paper
• On-line learning of a feedback controller for quasi-passive-dynamic walking by a stochastic policy gradient method

  2005cited by this paper
• Off-Policy Natural Actor-Critic

  2005influential reference
• Stochastic policy gradient reinforcement learning on a simple 3D biped

  2004cited by this paper
• Design of self-contained biped walker with pneumatic actuators

  2004cited by this paper
• Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning

  2004cited by this paper
• Natural Actor-Critic

  2003cited by this paper
• A novel gait generation for biped walking robots based on mechanical energy constraint

  2002cited by this paper
• A Natural Policy Gradient

  2001cited by this paper
• Policy Gradient Methods for Reinforcement Learning with Function Approximation

  1999cited by this paper
• An Analysis of Actor/Critic Algorithms Using Eligibility Traces: Reinforcement Learning with Imperfect Value Function

  1998cited by this paper
• Passive Dynamic Walking

  1990cited by this paper

• Efficient learning of stand-up motion for humanoid robots with bilateral symmetry

  2016cites this paper
• Single leg operational space control of quadruped robot based on reinforcement learning

  2016cites this paper
• Creative Adaptation through Learning

  2015cites this paper
• Behavior Adaptation by Means of Reinforcement Learning

  2013cites this paper
• Two-step gradient-based reinforcement learning for underwater robotics behavior learning

  2013cites this paper
• Control of a Bipedal Robot Walker on Rough Terrain

  2012cites this paper
• Gradient-based reinforcement learning techniques for underwater robotics behavior learning

  2011cites this paper
• Dynamic Walking on Uneven Terrains with Passivity-Based Bipedal Robots

  2011cites this paper
• Two steps natural actor critic learning for underwater cable tracking

  2010cites this paper
• Acquisition of energy-efficient bipedal walking using CPG-based reinforcement learning

  2009cites this paper
• Reinforcement learning of motor skills with policy gradients

  2008cites this paper
• Machine learning of motor skills for robotics

  2007cites this paper
• Motor control optimization of compliant one-legged locomotion in rough terrain

  2007cites this paper
• Reinforcement Learning of Stable Trajectory for Quasi-Passive Dynamic Walking of an Unstable Biped Robot

  2007cites this paper
• Natural Actor-Critic

  2003cites this paper