Multi-task reinforcement learning (MTRL) aims to learn several tasks simultaneously for better sample efficiency than learning them separately. Traditional methods achieve this by sharing parameters or relabeling data between tasks. In this work, we introduce a new framework for sharing behavioral policies across tasks, which can be used in addition to existing MTRL methods. The key idea is to improve each task's off-policy data collection by employing behaviors from other task policies. Selectively sharing helpful behaviors acquired in one task to collect training data for another task can lead to higher-quality trajectories, leading to more sample-efficient MTRL. Thus, we introduce a simple and principled framework called Q-switch mixture of policies (QMP) that selectively shares behavior between different task policies by using the task's Q-function to evaluate and select useful shareable behaviors. We theoretically analyze how QMP improves the sample efficiency of the underlying RL algorithm. Our experiments show that QMP's behavioral policy sharing provides complementary gains over many popular MTRL algorithms and outperforms alternative ways to share behaviors in various manipulation, locomotion, and navigation environments. Videos are available at https://qmp-mtrl.github.io/.

We propose a framework to learn semantics from raw audio signals using two types of representations, encoding contextual and phonetic information respectively. Specifically, we introduce a speech-to-unit processing pipeline that captures two types of representations with different time resolutions. For the language model, we adopt a dual-channel architecture to incorporate both types of representation. We also present new training objectives, masked context reconstruction and masked context prediction, that push models to learn semantics effectively. Experiments on the sSIMI metric of Zero Resource Speech Benchmark 2021 and Fluent Speech Command dataset show our framework learns semantics better than models trained with only one type of representation.

Active learning is widely used to reduce labeling effort and training time by repeatedly querying only the most beneficial samples from unlabeled data. In real-world problems where data cannot be stored indefinitely due to limited storage or privacy issues, the query selection and the model update should be performed as soon as a new data sample is observed. Various online active learning methods have been studied to deal with these challenges; however, there are difficulties in selecting representative query samples and updating the model efficiently without forgetting. In this study, we propose Message Passing Adaptive Resonance Theory (MPART) that learns the distribution and topology of input data online. Through message passing on the topological graph, MPART actively queries informative and representative samples, and continuously improves the classification performance using both labeled and unlabeled data. We evaluate our model in stream-based selective sampling scenarios with comparable query selection strategies, showing that MPART significantly outperforms competitive models.

Semi-supervised learning and continuous learning are fundamental paradigms for human-level intelligence. To deal with real-world problems where labels are rarely given and the opportunity to access the same data is limited, it is necessary to apply these two paradigms in a joined fashion. In this paper, we propose Label Propagation Adaptive Resonance Theory (LPART) for semi-supervised continuous learning. LPART uses an online label propagation mechanism to perform classification and gradually improves its accuracy as the observed data accumulates. We evaluated the proposed model on visual (MNIST, SVHN, CIFAR-10) and audio (NSynth) datasets by adjusting the ratio of the labeled and unlabeled data. The accuracies are much higher when both labeled and unlabeled data are used, demonstrating the significant advantage of LPART in environments where the data labels are scarce.