论文信息 - Reinforcement learning of walking behavior for a four-legged robot

Reinforcement learning of walking behavior for a four-legged robot

In this paper, we investigate a reinforcement learning of walking behavior for a four-legged robot. The robot has two servo motors per leg, so this problem has eight-dimensional continuous state/action space. We present an action selection scheme for actor-critic algorithms, in which the actor selects a continuous action from its bounded action space by using the normal distribution. The experimental results show the robot successfully learns to walk in practical learning steps.

[1] Jun Morimoto,et al. Acquisition of stand-up behavior by a real robot using hierarchical reinforcement learning , 2000, Robotics Auton. Syst..

[2] Yishay Mansour,et al. Policy Gradient Methods for Reinforcement Learning with Function Approximation , 1999, NIPS.

[3] Vijay R. Konda,et al. Actor-Critic Algorithms , 1999, NIPS.

[4] Shigenobu Kobayashi,et al. An Analysis of Actor/Critic Algorithms Using Eligibility Traces: Reinforcement Learning with Imperfect Value Function , 1998, ICML.

[5] Ashwin Ram,et al. Experiments with Reinforcement Learning in Problems with Continuous State and Action Spaces , 1997, Adapt. Behav..

[6] Kenji Doya,et al. Efficient Nonlinear Control with Actor-Tutor Architecture , 1996, NIPS.

[7] John N. Tsitsiklis,et al. Analysis of Temporal-Diffference Learning with Function Approximation , 1996, NIPS.

[8] Richard S. Sutton,et al. Neuronlike adaptive elements that can solve difficult learning control problems , 1983, IEEE Transactions on Systems, Man, and Cybernetics.