Part of Advances in Neural Information Processing Systems 36 (NeurIPS 2023) Main Conference Track
Denis Blessing, Onur Celik, Xiaogang Jia, Moritz Reuss, Maximilian Li, Rudolf Lioutikov, Gerhard Neumann
Imitation learning uses data for training policies to solve complex tasks. However,when the training data is collected from human demonstrators, it often leadsto multimodal distributions because of the variability in human actions. Mostimitation learning methods rely on a maximum likelihood (ML) objective to learna parameterized policy, but this can result in suboptimal or unsafe behavior dueto the mode-averaging property of the ML objective. In this work, we proposeInformation Maximizing Curriculum, a curriculum-based approach that assignsa weight to each data point and encourages the model to specialize in the data itcan represent, effectively mitigating the mode-averaging problem by allowing themodel to ignore data from modes it cannot represent. To cover all modes and thus,enable versatile behavior, we extend our approach to a mixture of experts (MoE)policy, where each mixture component selects its own subset of the training datafor learning. A novel, maximum entropy-based objective is proposed to achievefull coverage of the dataset, thereby enabling the policy to encompass all modeswithin the data distribution. We demonstrate the effectiveness of our approach oncomplex simulated control tasks using versatile human demonstrations, achievingsuperior performance compared to state-of-the-art methods.