Games have a long history of serving as a benchmark for progress in artificial intelligence. Recently, approaches using search and learning have shown strong performance across a set of perfect information games, and approaches using game-theoretic reasoning and learning have shown strong performance for specific imperfect information poker variants. We introduce Player of Games, a general-purpose algorithm that unifies previous approaches, combining guided search, self-play learning, and game-theoretic reasoning. Player of Games is the first algorithm to achieve strong empirical performance in large perfect and imperfect information games -- an important step towards truly general algorithms for arbitrary environments. We prove that Player of Games is sound, converging to perfect play as available computation time and approximation capacity increases. Player of Games reaches strong performance in chess and Go, beats the strongest openly available agent in heads-up no-limit Texas hold'em poker (Slumbot), and defeats the state-of-the-art agent in Scotland Yard, an imperfect information game that illustrates the value of guided search, learning, and game-theoretic reasoning.
Mainstream Video-Language Pre-training models \cite{actbert,clipbert,violet} consist of three parts, a video encoder, a text encoder, and a video-text fusion Transformer. They pursue better performance via utilizing heavier unimodal encoders or multimodal fusion Transformers, resulting in increased parameters with lower efficiency in downstream tasks. In this work, we for the first time introduce an end-to-end video-language model, namely \textit{all-in-one Transformer}, that embeds raw video and textual signals into joint representations using a unified backbone architecture. We argue that the unique temporal information of video data turns out to be a key barrier hindering the design of a modality-agnostic Transformer. To overcome the challenge, we introduce a novel and effective token rolling operation to encode temporal representations from video clips in a non-parametric manner. The careful design enables the representation learning of both video-text multimodal inputs and unimodal inputs using a unified backbone model. Our pre-trained all-in-one Transformer is transferred to various downstream video-text tasks after fine-tuning, including text-video retrieval, video-question answering, multiple choice and visual commonsense reasoning. State-of-the-art performances with the minimal model FLOPs on nine datasets demonstrate the superiority of our method compared to the competitive counterparts. The code and pretrained model have been released in https://github.com/showlab/all-in-one.
Motivated by applications in cognitive radio networks, we consider the decentralized multi-player multi-armed bandit problem, without collision nor sensing information. We propose Randomized Selfish KL-UCB, an algorithm with very low computational complexity, inspired by the Selfish KL-UCB algorithm, which has been abandoned as it provably performs sub-optimally in some cases. We subject Randomized Selfish KL-UCB to extensive numerical experiments showing that it far outperforms state-of-the-art algorithms in almost all environments, sometimes by several orders of magnitude, and without the additional knowledge required by state-of-the-art algorithms. We also emphasize the potential of this algorithm for the more realistic dynamic setting, and support our claims with further experiments. We believe that the low complexity and high performance of Randomized Selfish KL-UCB makes it the most suitable for implementation in practical systems amongst known algorithms.
The demand for robot exploration in unstructured and unknown environments has recently grown substantially thanks to the host of inexpensive sensing and edge-computing solutions. In order to come closer to full autonomy, robots need to process the measurement stream in real-time, which calls for efficient exploration strategies. Information-based exploration techniques, such as Cauchy-Schwarz quadratic mutual information (CSQMI) and fast Shannon mutual information (FSMI), have successfully achieved active binary occupancy mapping with range measurements. However, as we envision robots performing complex tasks specified with semantically meaningful objects, it is necessary to capture semantic categories in the measurements, map representation, and exploration objective. In this work we propose a Bayesian multi-class mapping algorithm utilizing range-category measurements, as well as a closed-form efficiently computable lower bound for the Shannon mutual information between the multi-class map and the measurements. The bound allows rapid evaluation of many potential robot trajectories for autonomous exploration and mapping. Furthermore, we develop a compressed representation of 3-D environments with semantic labels based on OcTree data structure, where each voxel maintains a categorical distribution over object classes. The proposed 3-D representation facilitates fast computation of Shannon mutual information between the semantic Octomap and the measurements using Run-Length Encoding (RLE) of range-category observation rays. We compare our method against frontier-based and FSMI exploration and apply it in a variety of simulated and real-world experiments.
We develop data processing inequalities that describe how Fisher information from statistical samples can scale with the privacy parameter $\varepsilon$ under local differential privacy constraints. These bounds are valid under general conditions on the distribution of the score of the statistical model, and they elucidate under which conditions the dependence on $\varepsilon$ is linear, quadratic, or exponential. We show how these inequalities imply order optimal lower bounds for private estimation for both the Gaussian location model and discrete distribution estimation for all levels of privacy $\varepsilon>0$. We further apply these inequalities to sparse Bernoulli models and demonstrate privacy mechanisms and estimators with order-matching squared $\ell^2$ error.
We propose a novel Reinforcement Learning model for discrete environments, which is inherently interpretable and supports the discovery of deep subgoal hierarchies. In the model, an agent learns information about environment in the form of probabilistic rules, while policies for (sub)goals are learned as combinations thereof. No reward function is required for learning; an agent only needs to be given a primary goal to achieve. Subgoals of a goal G from the hierarchy are computed as descriptions of states, which if previously achieved increase the total efficiency of the available policies for G. These state descriptions are introduced as new sensor predicates into the rule language of the agent, which allows for sensing important intermediate states and for updating environment rules and policies accordingly.
Weak Supervision (WS) techniques allow users to efficiently create large training datasets by programmatically labeling data with heuristic sources of supervision. While the success of WS relies heavily on the provided labeling heuristics, the process of how these heuristics are created in practice has remained under-explored. In this work, we formalize the development process of labeling heuristics as an interactive procedure, built around the existing workflow where users draw ideas from a selected set of development data for designing the heuristic sources. With the formalism, we study two core problems of how to strategically select the development data to guide users in efficiently creating informative heuristics, and how to exploit the information within the development process to contextualize and better learn from the resultant heuristics. Building upon two novel methodologies that effectively tackle the respective problems considered, we present Nemo, an end-to-end interactive system that improves the overall productivity of WS learning pipeline by an average 20% (and up to 47% in one task) compared to the prevailing WS approach.
Panoramic images with their 360-degree directional view encompass exhaustive information about the surrounding space, providing a rich foundation for scene understanding. To unfold this potential in the form of robust panoramic segmentation models, large quantities of expensive, pixel-wise annotations are crucial for success. Such annotations are available, but predominantly for narrow-angle, pinhole-camera images which, off the shelf, serve as sub-optimal resources for training panoramic models. Distortions and the distinct image-feature distribution in 360-degree panoramas impede the transfer from the annotation-rich pinhole domain and therefore come with a big dent in performance. To get around this domain difference and bring together semantic annotations from pinhole- and 360-degree surround-visuals, we propose to learn object deformations and panoramic image distortions in the Deformable Patch Embedding (DPE) and Deformable MLP (DMLP) components which blend into our Transformer for PAnoramic Semantic Segmentation (Trans4PASS) model. Finally, we tie together shared semantics in pinhole- and panoramic feature embeddings by generating multi-scale prototype features and aligning them in our Mutual Prototypical Adaptation (MPA) for unsupervised domain adaptation. On the indoor Stanford2D3D dataset, our Trans4PASS with MPA maintains comparable performance to fully-supervised state-of-the-arts, cutting the need for over 1,400 labeled panoramas. On the outdoor DensePASS dataset, we break state-of-the-art by 14.39% mIoU and set the new bar at 56.38%. Code will be made publicly available at https://github.com/jamycheung/Trans4PASS.
We propose a novel robust decentralized graph clustering algorithm that is provably equivalent to the popular spectral clustering approach. Our proposed method uses the existing wave equation clustering algorithm that is based on propagating waves through the graph. However, instead of using a fast Fourier transform (FFT) computation at every node, our proposed approach exploits the Koopman operator framework. Specifically, we show that propagating waves in the graph followed by a local dynamic mode decomposition (DMD) computation at every node is capable of retrieving the eigenvalues and the local eigenvector components of the graph Laplacian, thereby providing local cluster assignments for all nodes. We demonstrate that the DMD computation is more robust than the existing FFT based approach and requires 20 times fewer steps of the wave equation to accurately recover the clustering information and reduces the relative error by orders of magnitude. We demonstrate the decentralized approach on a range of graph clustering problems.
Large-scale perturbations in the microbiome constitution are strongly correlated, whether as a driver or a consequence, with the health and functioning of human physiology. However, understanding the difference in the microbiome profiles of healthy and ill individuals can be complicated due to the large number of complex interactions among microbes. We propose to model these interactions as a time-evolving graph whose nodes are microbes and edges are interactions among them. Motivated by the need to analyse such complex interactions, we develop a method that learns a low-dimensional representation of the time-evolving graph and maintains the dynamics occurring in the high-dimensional space. Through our experiments, we show that we can extract graph features such as clusters of nodes or edges that have the highest impact on the model to learn the low-dimensional representation. This information can be crucial to identify microbes and interactions among them that are strongly correlated with clinical diseases. We conduct our experiments on both synthetic and real-world microbiome datasets.