Reinforcement learning of walking behavior for a four-legged robot

By Hajime Kimura, Toru Yamashita, Shigenobu Kobayashi. 2001

116 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Biomedical Engineering, Molecular Biology

How researchers see this paper

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

In Artificial Intelligence

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

In Biomedical Engineering

1. Jan Peters
2. Jens Kober
3. J. Bagnell
4. Sergey Levine
5. Jun Morimoto
6. Pieter Abbeel
7. Jun Nakanishi
8. Kenji Doya

In Molecular Biology

1. Jens Kober
2. Jan Peters
3. J. Bagnell
4. Kenji Doya
5. Christina Heinze-Deml
6. Nicolai Meinshausen

Citations in the corpus

• Reinforcement learning in robotics: A survey (2013, background): “Example applications include balancing a ball on a beam (Benbrahim et al., 1992), one-DoF ball in a cup (Nemec et al., 2010), two-DoF crawling motions (Tokic et al., 2009), and gait patterns for four-legged walking (Kimura et al., 2001).”
• Model-Free reinforcement learning with continuous action in practice (2012, unknown): “Algorithm AC is similar to that introduced by Kimura [11] (without the theoretical justification presented in this paper).”
• Ieee Transactions on Systems, Man and Cybernetics—part C: Applications and Reviews 1 a Survey of Actor-critic Reinforcement Learning: Standard and Natural Policy Gradients (unknown): “Barto et al. [46], FACRLN [53], [54], CACM [55], Bhatnagar [56], Chun-Gui et al. [57], Kimura et al. [58], Raju et al. [59] (e)NAC [16], [52], Park et al. [60], Girgin and Preux [61], Kimura [62],Richter et al. [2], Kim et al. [63], Nakamura et al. [64], El-Fakdi et al. [65] Average return”
• Closed-Loop Learning of Visual Control Policies (2011, unknown): “Backgammon player (Tesauro, 1995), solving the Acrobot control problem (Yoshimoto, Ishii, & Sato, 1999), making a quadruped robot learn progressively to walk without any human intervention (Huber & Grupen, 1998; Kimura, Yamashita, & Kobayashi, 2001; Kohl & Stone, 2004), riding a bicycle (Randlov &”
• Learning CPG-based biped locomotion with a policy gradient method (2005, methodology): “Moreover, the effectiveness of the policy gradient method in POMDPs has been empirically demonstrated for a 4-legged robot [14] and a passive-dynamics based biped robot [15].”
• Free gait generation with reinforcement learning for a six-legged robot (2008, background): “[16], aim learning of sequential angular positions of the actuators of a four-legged robot in order to maximize the speed.”