Partner diversity is known to be crucial for training a robust generalist cooperative agent. In this paper, we show that partner specialization, in addition to diversity, is crucial for the robustness of a downstream generalist agent. We propose a principled method for quantifying both the diversity and specialization of a partner population based on the concept of mutual information. Then, we observe that the recently proposed cross-play minimization (XP-min) technique produces diverse and specialized partners. However, the generated partners are overfit, reducing their usefulness as training partners. To address this, we propose simple methods, based on reinforcement learning and supervised learning, for extracting the diverse and specialized behaviors of XP-min generated partners but not their overfitness. We demonstrate empirically that the proposed method effectively removes overfitness, and extracted populations produce more robust generalist agents compared to the source XP-min populations.

A conventional adopted method for operating a waiter robot is based on the static position control, where predefined goal positions are marked on a map. However, this solution is not optimal in a dynamic setting, such as in a coffee shop or an outdoor catering event, because the customers often change their positions. This article explores an alternative human-robot interface design where a human operator communicates the identity of the customer to the robot instead. Inspired by how human communicates, we propose a framework for communicating a visual goal to the robot, through interactive two-way communications. The framework exploits concepts from two machine learning domains: human-in-the-loop machine learning, where active learning is used to acquire informative data, and deep metric learning, where a suitable embedding can improve the learning ability of a classifier. We also propose novel class imbalance handling techniques, which aim to actively alleviate the class imbalance problem found to be important in this mode of communication. The framework is evaluated using publicly available pedestrian datasets. We demonstrate that the proposed framework can help reduce the number of required two-way interactions and increases the robustness of the predictive model. We successfully implement the framework on a mobile robot for a delivery service in a cafe-like environment. Through the online visual goal human-robot communication, the robot can detect, recognize, and autonomously navigate to the target customer.

Identifying bio-signals based-sleep stages requires time-consuming and tedious labor of skilled clinicians. Deep learning approaches have been introduced in order to challenge the automatic sleep stage classification conundrum. However, the difficulties can be posed in replacing the clinicians with the automatic system due to the differences in many aspects found in individual bio-signals, causing the inconsistency in the performance of the model on every incoming individual. Thus, we aim to explore the feasibility of using a novel approach, capable of assisting the clinicians and lessening the workload. We propose the transfer learning framework, entitled MetaSleepLearner, based on Model Agnostic Meta-Learning (MAML), in order to transfer the acquired sleep staging knowledge from a large dataset to new individual subjects (source code is available at https://github.com/IoBT-VISTEC/MetaSleepLearner). The framework was demonstrated to require the labelling of only a few sleep epochs by the clinicians and allow the remainder to be handled by the system. Layer-wise Relevance Propagation (LRP) was also applied to understand the learning course of our approach. In all acquired datasets, in comparison to the conventional approach, MetaSleepLearner achieved a range of 5.4% to 17.7% improvement with statistical difference in the mean of both approaches. The illustration of the model interpretation after the adaptation to each subject also confirmed that the performance was directed towards reasonable learning. MetaSleepLearner outperformed the conventional approaches as a result from the fine-tuning using the recordings of both healthy subjects and patients. This is the first work that investigated a non-conventional pre-training method, MAML, resulting in a possibility for human-machine collaboration in sleep stage classification and easing the burden of the clinicians in labelling the sleep stages through only several epochs rather than an entire recording.

One of the main concerns of deep reinforcement learning (DRL) is the data inefficiency problem, which stems both from an inability to fully utilize data acquired and from naive exploration strategies. In order to alleviate these problems, we propose a DRL algorithm that aims to improve data efficiency via both the utilization of unrewarded experiences and the exploration strategy by combining ideas from unsupervised auxiliary tasks, intrinsic motivation, and hierarchical reinforcement learning (HRL). Our method is based on a simple HRL architecture with a metacontroller and a subcontroller. The subcontroller is intrinsically motivated by the metacontroller to learn to control aspects of the environment, with the intention of giving the agent: 1) a neural representation that is generically useful for tasks that involve manipulation of the environment and 2) the ability to explore the environment in a temporally extended manner through the control of the metacontroller. In this way, we reinterpret the notion of pixel- and feature-control auxiliary tasks as reusable skills that can be learned via an intrinsic reward. We evaluate our method on a number of Atari 2600 games. We found that it outperforms the baseline in several environments and significantly improves performance in one of the hardest games-Montezuma's revenge-for which the ability to utilize sparse data is key. We found that the inclusion of intrinsic reward is crucial for the improvement in the performance and that most of the benefit seems to be derived from the representations learned during training.