To learn from data collected in diverse dynamics, Imitation from Observation (IfO) methods leverage expert state trajectories based on the premise that recovering expert state distributions in other dynamics facilitates policy learning in the current one. However, Imitation Learning inherently imposes a performance upper bound of learned policies. Additionally, as the environment dynamics change, certain expert states may become inaccessible, rendering their distributions less valuable for imitation. To address this, we propose a novel framework that integrates reward maximization with IfO, employing F-distance regularized policy optimization. This framework enforces constraints on globally accessible states—those with nonzero visitation frequency across all considered dynamics—mitigating the challenge posed by inaccessible states. By instantiating F-distance in different ways, we derive two theoretical analysis and develop a practical algorithm called Accessible State Oriented Policy Regularization (ASOR). ASOR serves as a general-purpose module that can be incorporated into various RL approaches, including offline RL and off-policy RL. Extensive experiments across multiple benchmarks demonstrate ASOR’s effectiveness in enhancing state-of-the-art cross-domain policy transfer algorithms, significantly improving their performance.

Online experimentation, also known as A/B testing, is the gold standard for measuring product impacts and making business decisions in the tech industry. The validity and utility of experiments, however, hinge on unbiasedness and sufficient power. In two-sided online marketplaces, both requirements are called into question. The Bernoulli randomized experiments are biased because treatment units interfere with control units through market competition and violate the "stable unit treatment value assumption"(SUTVA). The experimental power on at least one side of the market is often insufficient because of disparate sample sizes on the two sides. Despite the importance of online marketplaces to the online economy and the crucial role experimentation plays in product development, there lacks an effective and practical solution to the bias and low power problems in marketplace experimentation. In this paper we address this shortcoming by proposing the budget-split design, which is unbiased in any marketplace where buyers have a finite or infinite budget. We show that it is more powerful than all other unbiased designs in the literature. We then provide a generalizable system architecture for deploying this design to online marketplaces. Finally, we confirm the effectiveness of our proposal with empirical performance from experiments run in two real-world online marketplaces. We demonstrate how it achieves over 15x gain in experimental power and removes market competition induced bias, which can be up to 230% the treatment effect size.

In this paper, we propose a power control algorithm dedicated for machine type communications (MTC) in future non-orthogonal multiple access (NOMA) networks employing game theory. In MTC networks, communication reliability should be considered prior to power consumption or energy efficiency. Once the reliability is satisfied, discussions about power consumption makes sense. We build a cost function for each device based on a non-cooperative game model. The cost function reflects the power consumption as well as received signal-to-interference plus noise ratio (SINR) of each device. Since we assume the devices are battery-driven, the objective is to minimize the power consumption as much as possible provided that the received SINR of each device is kept beyond an acceptable level so that the reliability can be guaranteed. We derive the power control algorithm function and prove the convergence of this iteration algorithm and the unique existence of Nash equilibrium as well. The simulation results show that under the same constraints of maximum power consumption and minimum acceptable SINR, the proposed algorithm outperforms the conventional algorithms in terms of power consumption and power efficiency.

In this paper, we demonstrate that recently-developed sparse recovery algorithms can be used to improve source localization in reverberant environments. By formulating the localization problem in the frequency domain, we are able to efficiently incorporate information that exploits the reverberation instead of considering it a nuisance to be eliminated. In this formulation, localization becomes a joint-sparsity support recovery problem which can be solved using model-based methods. We also develop a location model which further improves performance. Using our approach, we are able to recover more sources that the number of sensors. In contrast to conventional wisdom, we demonstrate that reverberation is beneficial in source localization, as long as it known and properly accounted for.

Packet classification has been a fundamental processing pattern of modern networking devices. Today's high-performance routers use specialized hardware for packet classification, but such solutions suffer from prohibitive cost, high power consumption, and poor extensibility. On the other hand, software-based routers offer the best flexibility, but could only deliver limited performance (<;10Gbps). Recently, graphics processing units (GPUs) have been proved to be an efficient accelerator for software routers. In this work, we propose a GPU-based linear search framework for packet classification. The core of our framework is a metaprogramming technique that dramatically enhances the execution efficiency. Experimental results prove that our solution could outperform a CPU-based solution by a factor of 17, in terms of classification throughput. Our technique is scalable to large rule sets consisting of over 50K rules and thus provides a solid foundation for future applications of packet context inspection.