Reinforcement Learning for Biped Locomotion

By Masa-aki Sato, Yutaka Nakamura, Shin Ishii. 2002

38 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Ecology, Evolution, Behavior and Systematics, Small Animals

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

1. Jan Peters
2. Sergey Levine
3. Jens Kober
4. Marc Peter Deisenroth
5. Stefan Schaal
6. Pieter Abbeel
7. J. Bagnell
8. Gerhard Neumann

In Ecology, Evolution, Behavior and Systematics

1. Jan Peters
2. Jens Kober
3. J. Bagnell

In Small Animals

1. Jan Peters
2. Jens Kober
3. J. Bagnell
4. Marc Peter Deisenroth

Citations in the corpus

• Reinforcement learning in robotics: A survey (2013, methodology): “Using it for value function approximation has allowed learning a navigation task with obstacle avoidance (Smart and Kaelbling, 1998), a pole balancing task Schaal (1997) as well as an air hockey task (Bentivegna, 2004).”
• Learning CPG-based biped locomotion with a policy gradient method (2005, methodology): “As parameter optimization methods for CPG-based locomotion controllers, a genetic algorithm [5] and reinforcement learning [6] were applied to determine the open parameters of the CPG considering high dimensional state space.”
• Reinforcement learning of motor skills with policy gradients (2008, background): “This class of algorithms has been widely accepted by now and has been applied in a variety of settings (Guenter, Hersch, Calinon, & Billard, in press; Mori et al., 2004; Mori, Nakamura, & Ishii, 2005; Nakamura et al., 2004; Park, Kim, & Kang, 2005; Richter, Aberdeen, & Yu, 2007; Sato et al., 2002; ”
• Toward fast policy search for learning legged locomotion (2012, background): “There have been a series of applications of machine learning approaches in legged locomotion such as Imitation Learning [20] and Reinforcement Learning (RL) [24], [22].”