Learning CPG-based Biped Locomotion with a Policy Gradient Method: Application to a Humanoid Robot

By Gen Endo, Jun Morimoto, Takamitsu Matsubara, Jun Nakanishi, Gordon Cheng. 2008

296 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Cell Biology, Genetics, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Cell Biology

In Genetics

In Reinforcement Learning

Citations in the corpus

End-to-End Training of Deep Visuomotor Policies (2015, background): “They have been applied to a range of robotic tasks, including manipulation [2, 13] and locomotion [5, 7, 15, 39].”
Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates (2016, methodology): “Reinforcement learning (RL) methods have been applied to range of robotic control tasks, from locomotion [1], [2] to manipulation [3], [4], [5], [6] and autonomous vehicle control [7].”
Reinforcement learning in robotics: A survey (2013, methodology): “Neural oscillators with sensor feedback have been used to learn rhythmic movements where open- and closed-loop information were combined, such as gaits for a two-legged robot (Geng et al., 2006; Endo et al., 2008).”
Deep spatial autoencoders for visuomotor learning (2015, methodology): “Reinforcement learning and policy search methods have been applied to perform a variety of robotic tasks, such as table tennis [9], object manipulation [10], [11], and locomotion [12], [13], [14], [15].”
Learning contact-rich manipulation skills with guided policy search (2015, methodology): “Previous policy search methods in robotics generally use one or more of the following techniques to achieve good performance and reasonable training times: the use of example demonstrations [15], [9], [16], the use of a prior controller that allows the policy to only set high level targets, such as ”
Virtual to Real Reinforcement Learning for Autonomous Driving (2017, background): “Reinforcement learning has been applied to a wide variety of robotics related tasks, such as computer games [17], robot locomotion [8, 12], and autonomous driving [1, 25].”
Deep reinforcement learning for tensegrity robot locomotion (2016, background): “Robotic learning methods have successfully learned locomotion policies for bipeds [2], [11], [12] and quadrupeds [3].”
Learning deep control policies for autonomous aerial vehicles with MPC-guided policy search (2015, methodology): “RL has been used to train robotic controllers for games such as ball-in-cup and table tennis [16], manipulation [31], [6], and robotic locomotion [17], [40], [10], [8].”
Learning compound multi-step controllers under unknown dynamics (2015, background): “Policy search methods in robotics have been used to learn a variety of behaviors, ranging from games such as ball-incup [1], to manipulation [2], [3] and robotic locomotion [4]– [7].”
CIRL: Controllable Imitative Reinforcement Learning for Vision-based Self-driving (2018, methodology): “Deep-RL or RL algorithm has been applied to a wide variety of tasks, such as object recognition [21,22,23,24,25], computer games [26], robot locomotion [27], scene navigation [28] and autonomous driving in the simulators [29,6,30].”
Hierarchical Relative Entropy Policy Search (2014, unknown): “We show that our Hierarchical REPS can learn versatile solutions while also showing an increased performance in terms of learning speed and quality of the found policy in comparison to the nonhierarchical approach.”
Central pattern generators for locomotion control in animals and robots: A review (2008, unknown): “algorithms8 (Matsubara et al., 2006; Nakamura, Mori, Sato, & Ishii, 2007; Ogino, Katoh, Aono, Asada, & Hosoda, 2004; Sato, Nakamura, & Ishii, 2002) and heuristic optimization algorithms such as Powell’s method (Crespi & Ijspeert, 2008; Marbach & Ijspeert, 2005; Sproewitz, Moeckel, Maye, & Ijspeert, ”
Learning Visual Feature Spaces for Robotic Manipulation with Deep Spatial Autoencoders (2015, methodology): “Reinforcement learning and policy search methods have been applied to perform a variety of robotic tasks, such as table tennis [9], object manipulation [10], [11], and locomotion [12], [13], [14], [15].”
A Survey on Policy Search for Robotics (2013, background): “Step-based exploration strategies use different exploration noise at each time-step and can explore either in action space or in parameter space as we know from the discussion in the previous section.”
Learning to pour with a robot arm combining goal and shape learning for dynamic movement primitives (2011, background): “Also more traditional gradient approaches have shown good results in complex robot control tasks [20,21].”