2019/10/01 by Shruti Mishra, Mishra, Shruti, Abbas Abdolmaleki +7 · 1 voice · 6 citations
Chemistry · Computer Science · Mathematics · #Artificial Intelligence (cs.AI) #Artificial intelligence #Biochemistry #Biological activity #Chemistry #Computer science #Domain (mathematical analysis) #Evolutionary Algorithms and Applications #FOS: Computer and information sciences #Geometry #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Mathematical analysis #Mathematics #Reinforcement Learning in Robotics #Robotics (cs.RO) #Symmetry (geometry) #Teaching and Learning Programming #cs.AI #cs.LG #cs.RO #stat.ML
paper · pdf · doi:10.48550/arxiv.1910.00528
published in arXiv (Cornell University) (Cornell University)
arxiv created 2019/10/01 · openalex publication_date 2019/10/01 · arxiv updated 2019/10/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Invariances to translation, rotation and other spatial transformations are a hallmark of the laws of motion, and have widespread use in the natural sciences to reduce the dimensionality of systems of equations. In supervised learning, such as in image classification tasks, rotation, translation and scale invariances are used to augment training datasets. In this work, we use data augmentation in a similar way, exploiting symmetry in the quadruped domain of the DeepMind control suite (Tassa et al. 2018) to add to the trajectories experienced by the actor in the actor-critic algorithm of Abdolmaleki et al. (2018). In a data-limited regime, the agent using a set of experiences augmented through symmetry is able to learn faster. Our approach can be used to inject knowledge of invariances in the domain and task to augment learning in robots, and more generally, to speed up learning in realistic robotics applications.