Abstract-- Robotic manipulation stands as a largely unsolved problem despite significant advances in robotics and machine learning in recent years. One of the key challenges in manipulation is the exploration of the dynamics of the environment when there is continuous contact between the objects being manipulated. This paper proposes a model-based active exploration approach that enables efficient learning in sparse-reward robotic manipulation tasks. The proposed method estimates an information gain objective using an ensemble of probabilistic models and deploys model predictive control (MPC) to plan actions online that maximize the expected reward while also performing directed exploration. We evaluate our proposed algorithm in simulation and on a real robot, trained from Figure 1: Our active exploration strategy evaluated on a challenging scratch with our method, on a challenging ball pushing task Tilted Pushing task in simulation (left) and on the real robot (right). Our real-world robot experiment serves as sparse reward model in order to bring the ball to a target location. We believe that for of dexterous manipulation capabilities was one of the major robots to reach human-level manipulation skills, they must driving factors in the development of the human mind [1] actively explore and adapt to new instances of a task. Performing manipulation is cognitively highly demanding, forcing the We define active exploration as the directed search of the agent to reason not only about the impact of its actions on agent, during the learning process, for unvisited state-action itself, but also on the environment. This inherent complexity pairs that would maximize the agent's performance.

Mobile robots have been widely used in various aspects of human life. When a robot moves between different positions in the working area to perform the task, controlling motion to follow a pre-defined path is the primary task of a mobile robot. Furthermore, the robot must remain at its desired speed to cooperate with other agents. This paper presents a development of a motion controller, in which the fuzzy logic method is combined with a kinematic model of a differential drive robot. The simulation results are compared well with experimental results indicate that the method is effective and applicable for actual mobile robots.

We study the problem of learning generalized linear models under adversarial corruptions. We analyze a classical heuristic called the iterative trimmed maximum likelihood estimator which is known to be effective against label corruptions in practice. Under label corruptions, we prove that this simple estimator achieves minimax near-optimal risk on a wide range of generalized linear models, including Gaussian regression, Poisson regression and Binomial regression. Finally, we extend the estimator to the more challenging setting of label and covariate corruptions and demonstrate its robustness and optimality in that setting as well.

Each machine learning algorithm handles one specific problem, and this way beginners can dive into one of these to figure out solutions, one at a time. Here is a compilation of the top machine learning algorithms that are frequently used in all machine learning fields. Now, you can practice ML algorithms here. Forming relationships between two variables is almost the starting point of a model, and linear regression in machine learning achieves that. The relationship between the dependent and independent variables is established by aligning them on a regression line.

Explainable Artificial Intelligence (XAI) is a paradigm that delivers transparent models and decisions, which are easy to understand, analyze, and augment by a non-technical audience. Fuzzy Logic Systems (FLS) based XAI can provide an explainable framework, while also modeling uncertainties present in real-world environments, which renders it suitable for applications where explainability is a requirement. However, most real-life processes are not characterized by high levels of uncertainties alone; they are inherently time-dependent as well, i.e., the processes change with time. In this work, we present novel Temporal Type-2 FLS Based Approach for time-dependent XAI (TXAI) systems, which can account for the likelihood of a measurement's occurrence in the time domain using (the measurement's) frequency of occurrence. In Temporal Type-2 Fuzzy Sets (TT2FSs), a four-dimensional (4D) time-dependent membership function is developed where relations are used to construct the inter-relations between the elements of the universe of discourse and its frequency of occurrence. The TXAI system manifested better classification prowess, with 10-fold test datasets, with a mean recall of 95.40\% than a standard XAI system (based on non-temporal general type-2 (GT2) fuzzy sets) that had a mean recall of 87.04\%. TXAI also performed significantly better than most non-explainable AI systems between 3.95\%, to 19.04\% improvement gain in mean recall. In addition, TXAI can also outline the most likely time-dependent trajectories using the frequency of occurrence values embedded in the TXAI model; viz. given a rule at a determined time interval, what will be the next most likely rule at a subsequent time interval. In this regard, the proposed TXAI system can have profound implications for delineating the evolution of real-life time-dependent processes, such as behavioural or biological processes.

Maximum likelihood estimation (MLE) is the predominant algorithm for training text generation models. This paradigm relies on direct supervision examples, which is not applicable to many emerging applications, such as generating adversarial attacks or generating prompts to control language models. Reinforcement learning (RL) on the other hand offers a more flexible solution by allowing users to plug in arbitrary task metrics as reward. Yet previous RL algorithms for text generation, such as policy gradient (on-policy RL) and Q-learning (off-policy RL), are often notoriously inefficient or unstable to train due to the large sequence space and the sparse reward received only at the end of sequences. In this paper, we introduce a new RL formulation for text generation from the soft Q-learning (SQL) perspective. It enables us to draw from the latest RL advances, such as path consistency learning, to combine the best of on-/off-policy updates, and learn effectively from sparse reward. We apply the approach to a wide range of novel text generation tasks, including learning from noisy/negative examples, adversarial attacks, and prompt generation. Experiments show our approach consistently outperforms both task-specialized algorithms and the previous RL methods.

We investigate nonlinear instrumental variable (IV) regression given high-dimensional instruments. We propose a simple algorithm which combines kernelized IV methods and an arbitrary, adaptive regression algorithm, accessed as a black box. Our algorithm enjoys faster-rate convergence and adapts to the dimensionality of informative latent features, while avoiding an expensive minimax optimization procedure, which has been necessary to establish similar guarantees. It further brings the benefit of flexible machine learning models to quasi-Bayesian uncertainty quantification, likelihood-based model selection, and model averaging. Simulation studies demonstrate the competitive performance of our method.

Bayesian optimisation (BO) algorithms have shown remarkable success in applications involving expensive black-box functions. Traditionally BO has been set as a sequential decision-making process which estimates the utility of query points via an acquisition function and a prior over functions, such as a Gaussian process. Recently, however, a reformulation of BO via density-ratio estimation (BORE) allowed reinterpreting the acquisition function as a probabilistic binary classifier, removing the need for an explicit prior over functions and increasing scalability. In this paper, we present a theoretical analysis of BORE's regret and an extension of the algorithm with improved uncertainty estimates. We also show that BORE can be naturally extended to a batch optimisation setting by recasting the problem as approximate Bayesian inference. The resulting algorithms come equipped with theoretical performance guarantees and are assessed against other batch and sequential BO baselines in a series of experiments.

Despite recent advances in automated machine learning, model selection is still a complex and computationally intensive process. For Gaussian processes (GPs), selecting the kernel is a crucial task, often done manually by the expert. Additionally, evaluating the model selection criteria for Gaussian processes typically scales cubically in the sample size, rendering kernel search particularly computationally expensive. We propose a novel, efficient search method through a general, structured kernel space. Previous methods solved this task via Bayesian optimization and relied on measuring the distance between GP's directly in function space to construct a kernel-kernel. We present an alternative approach by defining a kernel-kernel over the symbolic representation of the statistical hypothesis that is associated with a kernel. We empirically show that this leads to a computationally more efficient way of searching through a discrete kernel space.

An appropriate level of arousal induces positive emotions, and a high arousal potential may provoke negative emotions. To explain the effect of arousal on emotional valence, we propose a novel mathematical framework of arousal potential variations in the dual process of human cognition: automatic and controlled. A suitable mathematical formulation to explain the emotions in the dual process is still absent. Our model associates free energy with arousal potential and its variations to explain emotional valence. Decreasing and increasing free energy consequently induce positive and negative emotions, respectively. We formalize a transition from the automatic to the controlled process in the dual process as a change of Bayesian prior. Further, we model emotional valence using free energy increase (FI) when one tries changing one's Bayesian prior and its reduction (FR) when one succeeds in recognizing the same stimuli with a changed prior and define three emotions: "interest," "confusion," and "boredom" using the variations. The results of our mathematical analysis comparing various Gaussian model parameters reveals the following: 1) prediction error (PR) increases FR (representing "interest") when the first prior variance is greater than the second prior variance, 2) PR decreases FR when the first prior variance is less than the second prior variance, and 3) the distance between priors' means always increases FR. We also discuss the association of the outcomes with emotions in the controlled process. The proposed mathematical model provides a general framework for predicting and controlling emotional valence in the dual process that varies with viewpoint and stimuli, as well as for understanding the contradictions in the effects of arousal on the valence.