We present a framework for learning to plan hierarchically in domains with unknown dynamics. We enhance planning performance by exploiting problem structure in several ways: (i) We simplify the search over plans by leveraging knowledge of skill objectives, (ii) Shorter plans are generated by enforcing aggressively hierarchical planning, (iii) We learn transition dynamics with sparse local models for better generalisation. Our framework decomposes transition dynamics into skill effects and success conditions, which allows fast planning by reasoning on effects, while learning conditions from interactions with the world. We propose a simple method for learning new abstract skills, using successful trajectories stemming from completing the goals of a curriculum. Learned skills are then refined to leverage other abstract skills and enhance subsequent planning. We show that both conditions and abstract skills can be learned simultaneously while planning, even in stochastic domains. Our method is validated in experiments of increasing complexity, with up to 2^100 states, showing superior planning to classic non-hierarchical planners or reinforcement learning methods. Applicability to real-world problems is demonstrated in a simulation-to-real transfer experiment on a robotic manipulator.

We can also see this visually. We can verify the convergence of the chains formally using the Gelman Rubin test. Values close to 1.0 mean convergence. We can also test for correlation between samples in the chains. We are aiming for zero auto-correlation to get "random" samples from the posterior distribution.

In Canadian author Margaret Atwood's book "Blind Assassins," she says that "touch comes before sight, before speech. It's the first language and the last, and it always tells the truth." While our sense of touch gives us a channel to feel the physical world, our eyes help us immediately understand the full picture of these tactile signals. Robots that have been programmed to see or feel can't use these signals quite as interchangeably. To better bridge this sensory gap, researchers from MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) have come up with a predictive artificial intelligence (AI) that can learn to see by touching, and learn to feel by seeing.

It's another week, and there's another AI sales pitch to tell us all that robots can reduce workload and teach students better. That teachers aren't good enough at differentiation: robots can spot the gaps in pupils' learning more quickly and, using sophisticated algorithms, come up with instant tasks to bridge the gap and pave the way to success. Sadly, the idea that AI can cure all ills has been around too long unchallenged – except by dinosaurs like me. Somehow we've all begun to believe that pupils are empty vessels and – worse still – they are programmable. We may live in a technological age and we may be up to our eyeballs in glitzy apps.

Sufficient supervised information is crucial for any machine learning models to boost performance. However, labeling data is expensive and sometimes difficult to obtain. Active learning is an approach to acquire annotations for data from a human oracle by selecting informative samples with a high probability to enhance performance. In recent emerging studies, a generative adversarial network (GAN) has been integrated with active learning to generate good candidates to be presented to the oracle. In this paper, we propose a novel model that is able to obtain labels for data in a cheaper manner without the need to query an oracle. In the model, a novel reward for each sample is devised to measure the degree of uncertainty, which is obtained from a classifier trained with existing labeled data. This reward is used to guide a conditional GAN to generate informative samples with a higher probability for a certain label. With extensive evaluations, we have confirmed the effectiveness of the model, showing that the generated samples are capable of improving the classification performance in popular image classification tasks.

Traditionally, most of the existing attribute learning methods are trained based on the consensus of annotations aggregated from a limited number of annotators. However, the consensus might fail in settings, especially when a wide spectrum of annotators with different interests and comprehension about the attribute words are involved. In this paper, we develop a novel multi-task method to understand and predict personalized attribute annotations. Regarding the attribute preference learning for each annotator as a specific task, we first propose a multi-level task parameter decomposition to capture the evolution from a highly popular opinion of the mass to highly personalized choices that are special for each person. Meanwhile, for personalized learning methods, ranking prediction is much more important than accurate classification. This motivates us to employ an Area Under ROC Curve (AUC) based loss function to improve our model. On top of the AUC-based loss, we propose an efficient method to evaluate the loss and gradients. Theoretically, we propose a novel closed-form solution for one of our non-convex subproblem, which leads to provable convergence behaviors. Furthermore, we also provide a generalization bound to guarantee a reasonable performance. Finally, empirical analysis consistently speaks to the efficacy of our proposed method.

Deep reinforcement learning algorithms have been shown to learn complex skills using only high-dimensional observations and scalar reward. Effective and intelligent exploration still remains an unresolved problem for reinforcement learning. Most contemporary reinforcement learning relies on simple heuristic strategies such as $\epsilon$-greedy exploration or adding Gaussian noise to actions. These heuristics, however, are unable to intelligently distinguish the well explored and the unexplored regions of the state space, which can lead to inefficient use of training time. We introduce entropy-based exploration (EBE) that enables an agent to explore efficiently the unexplored regions of the state space. EBE quantifies the agent's learning in a state using merely state dependent action values and adaptively explores the state space, i.e. more exploration for the unexplored region of the state space. We perform experiments on many environments including a simple linear environment, a simpler version of the breakout game and multiple first-person shooter (FPS) games of VizDoom platform. We demonstrate that EBE enables efficient exploration that ultimately results in faster learning without having to tune hyperparameters.

Recurrent neural networks (RNNs) have recently achieved remarkable successes in a number of applications. However, the huge sizes and computational burden of these models make it difficult for their deployment on edge devices. A practically effective approach is to reduce the overall storage and computation costs of RNNs by network pruning techniques. Despite their successful applications, those pruning methods based on Lasso either produce irregular sparse patterns in weight matrices, which is not helpful in practical speedup. To address these issues, we propose structured pruning method through neuron selection which can reduce the sizes of basic structures of RNNs. More specifically, we introduce two sets of binary random variables, which can be interpreted as gates or switches to the input neurons and the hidden neurons, respectively. We demonstrate that the corresponding optimization problem can be addressed by minimizing the L0 norm of the weight matrix. Finally, experimental results on language modeling and machine reading comprehension tasks have indicated the advantages of the proposed method in comparison with state-of-the-art pruning competitors. In particular, nearly 20 x practical speedup during inference was achieved without losing performance for language model on the Penn TreeBank dataset, indicating the promising performance of the proposed method

We build a theoretical framework for understanding practical meta-learning methods that enables the integration of sophisticated formalizations of task-similarity with the extensive literature on online convex optimization and sequential prediction algorithms. Our approach enables the task-similarity to be learned adaptively, provides sharper transfer-risk bounds in the setting of statistical learning-to-learn, and leads to straightforward derivations of average-case regret bounds for efficient algorithms in settings where the task-environment changes dynamically or the tasks share a certain geometric structure. We use our theory to modify several popular meta-learning algorithms and improve their training and meta-test-time performance on standard problems in few-shot and federated deep learning.

The University of South Carolina announced plans last week to open an artificial intelligence institute that give students and faculty a shared space for interdisciplinary collaboration. The institute, which the university hopes to have running by this fall, will focus on research to advance AI applications across a wide range of industries, Hossein Haj-Hariri, dean of the College of Engineering and Computing, told EdScoop. "[Industries] are already being transformed or will be transformed by artificial intelligence," Haj-Hariri said. "The window where we can really lead the injection of research into application areas is open," he said. To drive innovation and develop cutting-edge solutions using AI, the institute will draw on the knowledge and experience of students and faculty from all 15 colleges across the university's campus, making it a hub for interdisciplinary collaboration.