首页 /研究 /Behaviour Learning by a Reward-Penalty Algorithm : From Gait Learning to Obstacle Avoidance by Neural Networks
LOCOMOTION

Behaviour Learning by a Reward-Penalty Algorithm : From Gait Learning to Obstacle Avoidance by Neural Networks

Isabelle Sarda, Anne Johannet

发表年份
1995
引用次数
5

关键词

Obstacle avoidanceObstacleAdaptation (eye)Computer scienceArtificial neural networkGaitArtificial intelligenceTask (project management)Mobile robotMachine learning

相关论文

查看 LOCOMOTION 分类全部论文