Robotics research has been focusing on cooperative multi-agent problems, where agents must work together and communicate to achieve a shared objective. To tackle this challenge, we explore imitation learning algorithms. These methods learn a controller by observing demonstrations of an expert, such as the behaviour of a centralised omniscient controller, which can perceive the entire environment, including the state and observations of all agents. Performing tasks with complete knowledge of the state of a system is relatively easy, but centralised solutions might not be feasible in real scenarios since agents do not have direct access to the state but only to their observations. To overcome this issue, we train end-to-end Neural Networks that take as input local observations obtained from an omniscient centralised controller, i.e., the agents' sensor readings and the communications received, producing as output the action to be performed and the communication to be transmitted. This study concentrates on two cooperative tasks using a distributed controller: distributing the robots evenly in space and colouring them based on their position relative to others. While an explicit exchange of messages between the agents is required to solve the second task, in the first one, a communication protocol is unnecessary, although it may increase performance. The experiments are run in Enki, a high-performance open-source simulator for planar robots, which provides collision detection and limited physics support for robots evolving on a flat surface. Moreover, it can simulate groups of robots hundreds of times faster than real-time. The results show how applying a communication strategy improves the performance of the distributed model, letting it decide which actions to take almost as precisely and quickly as the expert controller.

Multi-rotor UAVs suffer from a restricted range and flight duration due to limited battery capacity. Autonomous landing on a 2D moving platform offers the possibility to replenish batteries and offload data, thus increasing the utility of the vehicle. Classical approaches rely on accurate, complex and difficult-to-derive models of the vehicle and the environment. Reinforcement learning (RL) provides an attractive alternative due to its ability to learn a suitable control policy exclusively from data during a training procedure. However, current methods require several hours to train, have limited success rates and depend on hyperparameters that need to be tuned by trial-and-error. We address all these issues in this work. First, we decompose the landing procedure into a sequence of simpler, but similar learning tasks. This is enabled by applying two instances of the same RL based controller trained for 1D motion for controlling the multi-rotor's movement in both the longitudinal and the lateral direction. Second, we introduce a powerful state space discretization technique that is based on i) kinematic modeling of the moving platform to derive information about the state space topology and ii) structuring the training as a sequential curriculum using transfer learning. Third, we leverage the kinematics model of the moving platform to also derive interpretable hyperparameters for the training process that ensure sufficient maneuverability of the multi-rotor vehicle. The training is performed using the tabular RL method Double Q-Learning. Through extensive simulations we show that the presented method significantly increases the rate of successful landings, while requiring less training time compared to other deep RL approaches. Finally, we deploy and demonstrate our algorithm on real hardware. For all evaluation scenarios we provide statistics on the agent's performance.

We propose and design recommendation systems that incentivize efficient exploration. Agents arrive sequentially, choose actions and receive rewards, drawn from fixed but unknown action-specific distributions. The recommendation system presents each agent with actions and rewards from a subsequence of past agents, chosen ex ante. Thus, the agents engage in sequential social learning, moderated by these subsequences. We asymptotically attain optimal regret rate for exploration, using a flexible frequentist behavioral model and mitigating rationality and commitment assumptions inherent in prior work. We suggest three components of effective recommendation systems: independent focus groups, group aggregators, and interlaced information structures.

The recent (re)popularization of deep learning methods increased the importance and need for the data even further. Similarly, the other subfields of theoretical and applied linguistics have also seen a shift towards more data-driven methods. As a result, availability of large and high-quality language data is essential for both linguistic research and practical NLP applications. In this paper, we present a comprehensive and critical survey of linguistic resources for Turkish.

In 1987, then-CEO of Apple Computer, John Sculley, unveiled a vision that he hoped would cement his legacy as more than just a former purveyor of soft drinks. Keynoting at the EDUCOM conference, he presented a 5-minute, 45-second video of a product that built upon some ideas he had presented in his autobiography the previous year. The video is a two-hander playlet. The main character is a snooty UC Berkeley university professor. The other is a bot, living inside what we'd now call a foldable tablet.

Due to the sweeping digitalization of processes, increasingly vast amounts of time series data are being produced. Accurate classification of such time series facilitates decision making in multiple domains. State-of-the-art classification accuracy is often achieved by ensemble learning where results are synthesized from multiple base models. This characteristic implies that ensemble learning needs substantial computing resources, preventing their use in resource-limited environments, such as in edge devices. To extend the applicability of ensemble learning, we propose the LightTS framework that compresses large ensembles into lightweight models while ensuring competitive accuracy. First, we propose adaptive ensemble distillation that assigns adaptive weights to different base models such that their varying classification capabilities contribute purposefully to the training of the lightweight model. Second, we propose means of identifying Pareto optimal settings w.r.t. model accuracy and model size, thus enabling users with a space budget to select the most accurate lightweight model. We report on experiments using 128 real-world time series sets and different types of base models that justify key decisions in the design of LightTS and provide evidence that LightTS is able to outperform competitors.

The issue of missing data poses a great challenge on boosting performance and application of deep learning models in the {\em Knowledge Tracing} (KT) problem. However, there has been the lack of understanding on the issue in the literature. %are not sufficient studies tackling this problem. In this work, to address this challenge, we adopt a subject-based training method to split and impute data by student IDs instead of row number splitting which we call non-subject based training. The benefit of subject-based training can retain the complete sequence for each student and hence achieve efficient training. Further, we leverage two existing deep generative frameworks, namely variational Autoencoders (VAE) and Longitudinal Variational Autoencoders (LVAE) frameworks and build LSTM kernels into them to form LSTM-VAE and LSTM LVAE (noted as VAE and LVAE for simplicity) models to generate quality data. In LVAE, a Gaussian Process (GP) model is trained to disentangle the correlation between the subject (i.e., student) descriptor information (e.g., age, gender) and the latent space. The paper finally compare the model performance between training the original data and training the data imputed with generated data from non-subject based model VAE-NS and subject-based training models (i.e., VAE and LVAE). We demonstrate that the generated data from LSTM-VAE and LSTM-LVAE can boost the original model performance by about 50%. Moreover, the original model just needs 10% more student data to surpass the original performance if the prediction model is small and 50\% more data if the prediction model is large with our proposed frameworks.

Soft robotics has opened a unique path to flexibility and environmental adaptability, learning from nature and reproducing biological behaviors. Nature implies answers for how to apply robots to real life. To find out how we learn from creatures to design and apply soft robots, in this Review, we propose a classification method to summarize soft robots based on different functions of biological systems: self-growing, self-healing, self-responsive, and self-circulatory. The bio-function based classification logic is presented to explain why we learn from creatures. State-of-art technologies, characteristics, pros, cons, challenges, and potential applications of these categories are analyzed to illustrate what we learned from creatures. By intersecting these categories, the existing and potential bio-inspired applications are overviewed and outlooked to finally find the answer, that is, how we learn from creatures.

Chain-of-thought prompting (CoT) advances the reasoning abilities of large language models (LLMs) and achieves superior performance in arithmetic, commonsense, and symbolic reasoning tasks. However, most CoT studies rely on carefully designed human-annotated rational chains to prompt the language model, which poses challenges for real-world applications where labeled training data is available without human-annotated rational chains. This creates barriers to applications of CoT prompting to these general tasks. This paper proposes a new strategy, Automate-CoT (Automatic Prompt Augmentation and Selection with Chain-of-Thought), that can bypass human engineering of CoTs by automatically augmenting rational chains from a small labeled dataset, and then pruning low-quality chains to construct a candidate pool of machine-generated rationale chains based on the labels. Finally, it selects the optimal combination of several rationale chains from the pool for CoT prompting by employing a variance-reduced policy gradient strategy to estimate the significance of each example in a black-box language model. Automate-CoT enables a quick adaptation of the CoT technique to different tasks. Experimental results demonstrate the effectiveness of our method, where state-of-the-art results are achieved on arithmetic reasoning (+2.7\%), commonsense reasoning (+3.4\%), symbolic reasoning (+3.2\%), and non-reasoning tasks (+2.5\%). Our code will be available at https://github.com/shizhediao/automate-cot.

Distilled self-supervised models have shown competitive performance and efficiency in recent years. However, there is a lack of experience in jointly distilling multiple self-supervised speech models. In our work, we performed Ensemble Knowledge Distillation (EKD) on various self-supervised speech models such as HuBERT, RobustHuBERT, and WavLM. We tried two different aggregation techniques, layerwise-average and layerwise-concatenation, to the representations of different teacher models and found that the former was more effective. On top of that, we proposed a multiple prediction head method for student models to predict different layer outputs of multiple teacher models simultaneously. The experimental results show that our method improves the performance of the distilled models on four downstream speech processing tasks, Phoneme Recognition, Speaker Identification, Emotion Recognition, and Automatic Speech Recognition in the hidden-set track of the SUPERB benchmark.