In various applications, the optimal policy in a strategic decision-making problem depends both on the environmental configuration and exogenous events. For these settings, we introduce Bilevel Optimization with Contextual Markov Decision Processes (BO-CMDP), a stochastic bilevel decision-making model, where the lower level consists of solving a contextual Markov Decision Process (CMDP). BO-CMDP can be viewed as a Stackelberg Game where the leader and a random context beyond the leader's control together decide the setup of (many) MDPs that (potentially multiple) followers best respond to. This framework extends beyond traditional bilevel optimization and finds relevance in diverse fields such as model design for MDPs, tax design, reward shaping and dynamic mechanism design. We propose a stochastic Hyper Policy Gradient Descent (HPGD) algorithm to solve BO-CMDP, and demonstrate its convergence. Notably, HPGD only utilizes observations of the followers' trajectories. Therefore, it allows followers to use any training procedure and the leader to be agnostic of the specific algorithm used, which aligns with various real-world scenarios. We further consider the setting when the leader can influence the training of followers and propose an accelerated algorithm. We empirically demonstrate the performance of our algorithm.
相關內容
The capability to navigate safely in an unstructured environment is crucial when deploying robotic systems in real-world scenarios. Recently, control barrier function (CBF) based approaches have been highly effective in synthesizing safety-critical controllers. In this work, we propose a novel CBF-based local planner comprised of two components: Vessel and Mariner. The Vessel is a novel scaling factor based CBF formulation that synthesizes CBFs using only point cloud data. The Mariner is a CBF-based preview control framework that is used to mitigate getting stuck in spurious equilibria during navigation. To demonstrate the efficacy of our proposed approach, we first compare the proposed point cloud based CBF formulation with other point cloud based CBF formulations. Then, we demonstrate the performance of our proposed approach and its integration with global planners using experimental studies on the Unitree B1 and Unitree Go2 quadruped robots in various environments.
Political actors frequently manipulate redistricting plans to gain electoral advantages, a process commonly known as gerrymandering. To address this problem, several states have implemented institutional reforms including the establishment of map-drawing commissions. It is difficult to assess the impact of such reforms because each state structures bundles of complex rules in different ways. We propose to model redistricting processes as a sequential game. The equilibrium solution to the game summarizes multi-step institutional interactions as a single dimensional score. This score measures the leeway political actors have over the partisan lean of the final plan. Using a differences-in-differences design, we demonstrate that reforms reduce partisan bias and increase competitiveness when they constrain partisan actors. We perform a counterfactual policy analysis to estimate the partisan effects of enacting recent institutional reforms nationwide. We find that instituting redistricting commissions generally reduces the current Republican advantage, but Michigan-style reforms would yield a much greater pro-Democratic effect than types of redistricting commissions adopted in Ohio and New York.
Off-dynamics Reinforcement Learning (ODRL) seeks to transfer a policy from a source environment to a target environment characterized by distinct yet similar dynamics. In this context, traditional RL agents depend excessively on the dynamics of the source environment, resulting in the discovery of policies that excel in this environment but fail to provide reasonable performance in the target one. In the few-shot framework, a limited number of transitions from the target environment are introduced to facilitate a more effective transfer. Addressing this challenge, we propose an innovative approach inspired by recent advancements in Imitation Learning and conservative RL algorithms. The proposed method introduces a penalty to regulate the trajectories generated by the source-trained policy. We evaluate our method across various environments representing diverse off-dynamics conditions, where access to the target environment is extremely limited. These experiments include high-dimensional systems relevant to real-world applications. Across most tested scenarios, our proposed method demonstrates performance improvements compared to existing baselines.
Accurate localization can be performed in visible light systems in non-line-of-sight (NLOS) scenarios by utilizing intelligent reflecting surfaces (IRSs), which are commonly in the form of mirror arrays with adjustable orientations. When signals transmitted from light emitting diodes (LEDs) are reflected from IRSs and collected by a receiver, the position of the receiver can be estimated based on power measurements by utilizing the known parameters of the LEDs and IRSs. Since the orientation vectors of IRS elements (mirrors) cannot be adjusted perfectly in practice, it is important to evaluate the effects of mismatches between desired and true orientations of IRS elements. In this study, we derive the misspecified Cramer-Rao lower bound (MCRB) and the mismatched maximum likelihood (MML) estimator for specifying the estimation performance and the lower bound in the presence of mismatches in IRS orientations. We also provide comparisons with the conventional maximum likelihood (ML) estimator and the CRB in absence of orientation mismatches for quantifying the effects of mismatches. It is shown that orientation mismatches can result in significant degradation in localization accuracy at high signal-to-noise ratios.
Hybrid intelligence aims to enhance decision-making, problem-solving, and overall system performance by combining the strengths of both, human cognitive abilities and artificial intelligence. With the rise of Large Language Models (LLM), progressively participating as smart agents to accelerate machine learning development, Hybrid Intelligence is becoming an increasingly important topic for effective interaction between humans and machines. This paper presents an approach to leverage Hybrid Intelligence towards sustainable and energy-aware machine learning. When developing machine learning models, final model performance commonly rules the optimization process while the efficiency of the process itself is often neglected. Moreover, in recent times, energy efficiency has become equally crucial due to the significant environmental impact of complex and large-scale computational processes. The contribution of this work covers the interactive inclusion of secondary knowledge sources through Human-in-the-loop (HITL) and LLM agents to stress out and further resolve inefficiencies in the machine learning development process.
Aiming to achieve ubiquitous global connectivity and target detection on the same platform with improved spectral/energy efficiency and reduced onboard hardware cost, low Earth orbit (LEO) satellite systems capable of simultaneously performing communications and radar have attracted significant attention. Designing such a joint system should address not only the challenges of integrating two functions but also the unique propagation characteristics of the satellites. To overcome severe echo signal path loss due to the high altitude of the satellite, we put forth a bistatic integrated sensing and communication (ISAC) framework with a radar receiver separated from the satellite. For robust and effective interference management, we employ rate-splitting multiple access (RSMA), which splits and encodes users messages into private and common streams. We optimize the dual-functional precoders to maximize the minimum rate among all users while satisfying the Cramer-Rao bound (CRB) constraints. Given the challenge of acquiring instantaneous channel state information (iCSI) for LEO satellites, we exploit the geometrical and statistical characteristics of the satellite channel. To develop an efficient optimization algorithm, semidefinite relaxation (SDR), sequential rank-1 constraint relaxation (SROCR), and successive convex approximation (SCA) are utilized. Numerical results show that the proposed framework efficiently performs both communication and radar, demonstrating superior interference control capabilities. Furthermore, it is validated that the common stream plays three vital roles: i) beamforming towards the radar target, ii) interference management between communications and radar, and iii) interference management among communication users.
Several applications in time series forecasting require predicting multiple steps ahead. Despite the vast amount of literature in the topic, both classical and recent deep learning based approaches have mostly focused on minimising performance averaged over the predicted window. We observe that this can lead to disparate distributions of errors across forecasting steps, especially for recent transformer architectures trained on popular forecasting benchmarks. That is, optimising performance on average can lead to undesirably large errors at specific time-steps. In this work, we present a Constrained Learning approach for long-term time series forecasting that aims to find the best model in terms of average performance that respects a user-defined upper bound on the loss at each time-step. We call our approach loss shaping constraints because it imposes constraints on the loss at each time step, and leverage recent duality results to show that despite its non-convexity, the resulting problem has a bounded duality gap. We propose a practical Primal-Dual algorithm to tackle it, and demonstrate that the proposed approach exhibits competitive average performance in time series forecasting benchmarks, while shaping the distribution of errors across the predicted window.
Advances in artificial intelligence often stem from the development of new environments that abstract real-world situations into a form where research can be done conveniently. This paper contributes such an environment based on ideas inspired by elementary Microeconomics. Agents learn to produce resources in a spatially complex world, trade them with one another, and consume those that they prefer. We show that the emergent production, consumption, and pricing behaviors respond to environmental conditions in the directions predicted by supply and demand shifts in Microeconomics. We also demonstrate settings where the agents' emergent prices for goods vary over space, reflecting the local abundance of goods. After the price disparities emerge, some agents then discover a niche of transporting goods between regions with different prevailing prices -- a profitable strategy because they can buy goods where they are cheap and sell them where they are expensive. Finally, in a series of ablation experiments, we investigate how choices in the environmental rewards, bartering actions, agent architecture, and ability to consume tradable goods can either aid or inhibit the emergence of this economic behavior. This work is part of the environment development branch of a research program that aims to build human-like artificial general intelligence through multi-agent interactions in simulated societies. By exploring which environment features are needed for the basic phenomena of elementary microeconomics to emerge automatically from learning, we arrive at an environment that differs from those studied in prior multi-agent reinforcement learning work along several dimensions. For example, the model incorporates heterogeneous tastes and physical abilities, and agents negotiate with one another as a grounded form of communication.
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 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.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191