亚洲男人的天堂2018av,欧美草比,久久久久久免费视频精选,国色天香在线看免费,久久久久亚洲av成人片仓井空

Humans can quickly learn new behaviors by leveraging background world knowledge. In contrast, agents trained with reinforcement learning (RL) typically learn behaviors from scratch. We thus propose a novel approach that uses the vast amounts of general and indexable world knowledge encoded in vision-language models (VLMs) pre-trained on Internet-scale data for embodied RL. We initialize policies with VLMs by using them as promptable representations: embeddings that are grounded in visual observations and encode semantic features based on the VLM's internal knowledge, as elicited through prompts that provide task context and auxiliary information. We evaluate our approach on visually-complex, long horizon RL tasks in Minecraft and robot navigation in Habitat. We find that our policies trained on embeddings extracted from general-purpose VLMs outperform equivalent policies trained on generic, non-promptable image embeddings. We also find our approach outperforms instruction-following methods and performs comparably to domain-specific embeddings.

Motivated by modern applications such as computerized adaptive testing, sequential rank aggregation, and heterogeneous data source selection, we study the problem of active sequential estimation, which involves adaptively selecting experiments for sequentially collected data. The goal is to design experiment selection rules for more accurate model estimation. Greedy information-based experiment selection methods, optimizing the information gain for one-step ahead, have been employed in practice thanks to their computational convenience, flexibility to context or task changes, and broad applicability. However, statistical analysis is restricted to one-dimensional cases due to the problem's combinatorial nature and the seemingly limited capacity of greedy algorithms, leaving the multidimensional problem open. In this study, we close the gap for multidimensional problems. In particular, we propose adopting a class of greedy experiment selection methods and provide statistical analysis for the maximum likelihood estimator following these selection rules. This class encompasses both existing methods and introduces new methods with improved numerical efficiency. We prove that these methods produce consistent and asymptotically normal estimators. Additionally, within a decision theory framework, we establish that the proposed methods achieve asymptotic optimality when the risk measure aligns with the selection rule. We also conduct extensive numerical studies on both simulated and real data to illustrate the efficacy of the proposed methods. From a technical perspective, we devise new analytical tools to address theoretical challenges. These analytical tools are of independent theoretical interest and may be reused in related problems involving stochastic approximation and sequential designs.

In this letter, we address the problem of exploration and metric-semantic mapping of multi-floor GPS-denied indoor environments using Size Weight and Power (SWaP) constrained aerial robots. Most previous work in exploration assumes that robot localization is solved. However, neglecting the state uncertainty of the agent can ultimately lead to cascading errors both in the resulting map and in the state of the agent itself. Furthermore, actions that reduce localization errors may be at direct odds with the exploration task. We propose a framework that balances the efficiency of exploration with actions that reduce the state uncertainty of the agent. In particular, our algorithmic approach for active metric-semantic SLAM is built upon sparse information abstracted from raw problem data, to make it suitable for SWaP-constrained robots. Furthermore, we integrate this framework within a fully autonomous aerial robotic system that achieves autonomous exploration in cluttered, 3D environments. From extensive real-world experiments, we showed that by including Semantic Loop Closure (SLC), we can reduce the robot pose estimation errors by over 90% in translation and approximately 75% in yaw, and the uncertainties in pose estimates and semantic maps by over 70% and 65%, respectively. Although discussed in the context of indoor multi-floor exploration, our system can be used for various other applications, such as infrastructure inspection and precision agriculture where reliable GPS data may not be available.

In this paper, a type of novel projection-based, time-divided reduced order model (ROM) is proposed for dynamic fluid-structure interaction (FSI) problems, where spatial and temporal dimensions are partitioned as follows: spatially, each kind of variable is separated from others in terms of its attribution (fluid/structure), its category (velocity/pressure) and its component (horizontal/vertical); temporally, basis functions are deliberately adopted in small time windows tailored through extensive numerical trials. By the combination of space and time decompositions, the proposed ROM enables prolonged simulations under prescribed accuracy thresholds. Numerical experiments are carried out by means of a numerical comparison between the proposed ROM and corresponding full-order model (FOM) on solving a benchmark problem of FSI with a vibrating elastic beam in the fluid flow, where the representation of basis function sets on perturbation parameters is investigated as well. Extensive numerical results demonstrate the accuracy and efficiency of the proposed ROM. The developed numerical techniques are dimension-independent, which can be seamlessly extended to high dimensional FSI problems.

Engineering change orders (ECOs) in late stages make minimal design fixes to recover from timing shifts due to excessive IR drops. This paper integrates IR-drop-aware timing analysis and ECO timing optimization using reinforcement learning (RL). The method operates after physical design and power grid synthesis, and rectifies IR-drop-induced timing degradation through gate sizing. It incorporates the Lagrangian relaxation (LR) technique into a novel RL framework, which trains a relational graph convolutional network (R-GCN) agent to sequentially size gates to fix timing violations. The R-GCN agent outperforms a classical LR-only algorithm: in an open 45nm technology, it (a) moves the Pareto front of the delay-area tradeoff curve to the left and (b) saves runtime over the classical method by running fast inference using trained models at iso-quality. The RL model is transferable across timing specifications, and transferable to unseen designs with zero-shot learning or fine tuning.

Learning a universal policy across different robot morphologies can significantly improve learning efficiency and enable zero-shot generalization to unseen morphologies. However, learning a highly performant universal policy requires sophisticated architectures like transformers (TF) that have larger memory and computational cost than simpler multi-layer perceptrons (MLP). To achieve both good performance like TF and high efficiency like MLP at inference time, we propose HyperDistill, which consists of: (1) A morphology-conditioned hypernetwork (HN) that generates robot-wise MLP policies, and (2) A policy distillation approach that is essential for successful training. We show that on UNIMAL, a benchmark with hundreds of diverse morphologies, HyperDistill performs as well as a universal TF teacher policy on both training and unseen test robots, but reduces model size by 6-14 times, and computational cost by 67-160 times in different environments. Our analysis attributes the efficiency advantage of HyperDistill at inference time to knowledge decoupling, i.e., the ability to decouple inter-task and intra-task knowledge, a general principle that could also be applied to improve inference efficiency in other domains.

The paper aims to address load imbalance caused by high in-degree distribution in graphs by applying the idea of rhizome to vertex-centric message-driven graph processing. Rhizome construction of the graph creates multiple named vertex address for any number of single large in-degree vertices. It then allows other vertices to point to any of the named addresses thus sharing the in-degree load. The rhizomes internally communicate and remain consistent to provide a unified and correct view of the vertex. Simulated experimental results show performance speed ups for BFS graph traversal on large chip sizes for the tested input graph datasets containing highly skewed in-degree distribution. The improvements come from sharing the in-degree compute workload among memory-processing elements and also lowering contention on the network-on-chip.

The accurate and interpretable prediction of future events in time-series data often requires the capturing of representative patterns (or referred to as states) underpinning the observed data. To this end, most existing studies focus on the representation and recognition of states, but ignore the changing transitional relations among them. In this paper, we present evolutionary state graph, a dynamic graph structure designed to systematically represent the evolving relations (edges) among states (nodes) along time. We conduct analysis on the dynamic graphs constructed from the time-series data and show that changes on the graph structures (e.g., edges connecting certain state nodes) can inform the occurrences of events (i.e., time-series fluctuation). Inspired by this, we propose a novel graph neural network model, Evolutionary State Graph Network (EvoNet), to encode the evolutionary state graph for accurate and interpretable time-series event prediction. Specifically, Evolutionary State Graph Network models both the node-level (state-to-state) and graph-level (segment-to-segment) propagation, and captures the node-graph (state-to-segment) interactions over time. Experimental results based on five real-world datasets show that our approach not only achieves clear improvements compared with 11 baselines, but also provides more insights towards explaining the results of event predictions.

This paper presents a new multi-objective deep reinforcement learning (MODRL) framework based on deep Q-networks. We propose the use of linear and non-linear methods to develop the MODRL framework that includes both single-policy and multi-policy strategies. The experimental results on two benchmark problems including the two-objective deep sea treasure environment and the three-objective mountain car problem indicate that the proposed framework is able to converge to the optimal Pareto solutions effectively. The proposed framework is generic, which allows implementation of different deep reinforcement learning algorithms in different complex environments. This therefore overcomes many difficulties involved with standard multi-objective reinforcement learning (MORL) methods existing in the current literature. The framework creates a platform as a testbed environment to develop methods for solving various problems associated with the current MORL. Details of the framework implementation can be referred to //www.deakin.edu.au/~thanhthi/drl.htm.

This paper introduces an online model for object detection in videos designed to run in real-time on low-powered mobile and embedded devices. Our approach combines fast single-image object detection with convolutional long short term memory (LSTM) layers to create an interweaved recurrent-convolutional architecture. Additionally, we propose an efficient Bottleneck-LSTM layer that significantly reduces computational cost compared to regular LSTMs. Our network achieves temporal awareness by using Bottleneck-LSTMs to refine and propagate feature maps across frames. This approach is substantially faster than existing detection methods in video, outperforming the fastest single-frame models in model size and computational cost while attaining accuracy comparable to much more expensive single-frame models on the Imagenet VID 2015 dataset. Our model reaches a real-time inference speed of up to 15 FPS on a mobile CPU.