Abstract:In this paper, we investigate preference-based reinforcement learning (PbRL) that allows reinforcement learning (RL) agents to learn from human feedback. This is particularly valuable when defining a fine-grain reward function is not feasible. However, this approach is inefficient and impractical for promoting deep exploration in hard-exploration tasks with long horizons and sparse rewards. To tackle this issue, we introduce LOPE: Learning Online with trajectory Preference guidancE, an end-to-end preference-guided RL framework that enhances exploration efficiency in hard-exploration tasks. Our intuition is that LOPE directly adjusts the focus of online exploration by considering human feedback as guidance, avoiding learning a separate reward model from preferences. Specifically, LOPE includes a two-step sequential policy optimization process consisting of trust-region-based policy improvement and preference guidance steps. We reformulate preference guidance as a novel trajectory-wise state marginal matching problem that minimizes the maximum mean discrepancy distance between the preferred trajectories and the learned policy. Furthermore, we provide a theoretical analysis to characterize the performance improvement bound and evaluate the LOPE's effectiveness. When assessed in various challenging hard-exploration environments, LOPE outperforms several state-of-the-art methods regarding convergence rate and overall performance. The code used in this study is available at \url{https://github.com/buaawgj/LOPE}.
Abstract:Designing motion control and planning algorithms for multilift systems remains challenging due to the complexities of dynamics, collision avoidance, actuator limits, and scalability. Existing methods that use optimization and distributed techniques effectively address these constraints and scalability issues. However, they often require substantial manual tuning, leading to suboptimal performance. This paper proposes Auto-Multilift, a novel framework that automates the tuning of model predictive controllers (MPCs) for multilift systems. We model the MPC cost functions with deep neural networks (DNNs), enabling fast online adaptation to various scenarios. We develop a distributed policy gradient algorithm to train these DNNs efficiently in a closed-loop manner. Central to our algorithm is distributed sensitivity propagation, which parallelizes gradient computation across quadrotors, focusing on actual system state sensitivities relative to key MPC parameters. We also provide theoretical guarantees for the convergence of this algorithm. Extensive simulations show rapid convergence and favorable scalability to a large number of quadrotors. Our method outperforms a state-of-the-art open-loop MPC tuning approach by effectively learning adaptive MPCs from trajectory tracking errors and handling the unique dynamics couplings within the multilift system. Additionally, our framework can learn an adaptive reference for reconfigurating the system when traversing through multiple narrow slots.
Abstract:As Embodied AI advances, it increasingly enables robots to handle the complexity of household manipulation tasks more effectively. However, the application of robots in these settings remains limited due to the scarcity of bimanual-mobile robot manipulation datasets. Existing datasets either focus solely on simple grasping tasks using single-arm robots without mobility, or collect sensor data limited to a narrow scope of sensory inputs. As a result, these datasets often fail to encapsulate the intricate and dynamic nature of real-world tasks that bimanual-mobile robots are expected to perform. To address these limitations, we introduce BRMData, a Bimanual-mobile Robot Manipulation Dataset designed specifically for household applications. The dataset includes 10 diverse household tasks, ranging from simple single-arm manipulation to more complex dual-arm and mobile manipulations. It is collected using multi-view and depth-sensing data acquisition strategies. Human-robot interactions and multi-object manipulations are integrated into the task designs to closely simulate real-world household applications. Moreover, we present a Manipulation Efficiency Score (MES) metric to evaluate both the precision and efficiency of robot manipulation methods. BRMData aims to drive the development of versatile robot manipulation technologies, specifically focusing on advancing imitation learning methods from human demonstrations. The dataset is now open-sourced and available at https://embodiedrobot.github.io/, enhancing research and development efforts in the field of Embodied Manipulation.
Abstract:Offline reinforcement learning (RL) aims to learn optimal policies from previously collected datasets. Recently, due to their powerful representational capabilities, diffusion models have shown significant potential as policy models for offline RL issues. However, previous offline RL algorithms based on diffusion policies generally adopt weighted regression to improve the policy. This approach optimizes the policy only using the collected actions and is sensitive to Q-values, which limits the potential for further performance enhancement. To this end, we propose a novel preferred-action-optimized diffusion policy for offline RL. In particular, an expressive conditional diffusion model is utilized to represent the diverse distribution of a behavior policy. Meanwhile, based on the diffusion model, preferred actions within the same behavior distribution are automatically generated through the critic function. Moreover, an anti-noise preference optimization is designed to achieve policy improvement by using the preferred actions, which can adapt to noise-preferred actions for stable training. Extensive experiments demonstrate that the proposed method provides competitive or superior performance compared to previous state-of-the-art offline RL methods, particularly in sparse reward tasks such as Kitchen and AntMaze. Additionally, we empirically prove the effectiveness of anti-noise preference optimization.
Abstract:Domain adaptive pose estimation aims to enable deep models trained on source domain (synthesized) datasets produce similar results on the target domain (real-world) datasets. The existing methods have made significant progress by conducting image-level or feature-level alignment. However, only aligning at a single level is not sufficient to fully bridge the domain gap and achieve excellent domain adaptive results. In this paper, we propose a multi-level domain adaptation aproach, which aligns different domains at the image, feature, and pose levels. Specifically, we first utilize image style transer to ensure that images from the source and target domains have a similar distribution. Subsequently, at the feature level, we employ adversarial training to make the features from the source and target domains preserve domain-invariant characeristics as much as possible. Finally, at the pose level, a self-supervised approach is utilized to enable the model to learn diverse knowledge, implicitly addressing the domain gap. Experimental results demonstrate that significant imrovement can be achieved by the proposed multi-level alignment method in pose estimation, which outperforms previous state-of-the-art in human pose by up to 2.4% and animal pose estimation by up to 3.1% for dogs and 1.4% for sheep.
Abstract:In recent years, there has been significant progress in the development of text-to-image generative models. Evaluating the quality of the generative models is one essential step in the development process. Unfortunately, the evaluation process could consume a significant amount of computational resources, making the required periodic evaluation of model performance (e.g., monitoring training progress) impractical. Therefore, we seek to improve the evaluation efficiency by selecting the representative subset of the text-image dataset. We systematically investigate the design choices, including the selection criteria (textural features or image-based metrics) and the selection granularity (prompt-level or set-level). We find that the insights from prior work on subset selection for training data do not generalize to this problem, and we propose FlashEval, an iterative search algorithm tailored to evaluation data selection. We demonstrate the effectiveness of FlashEval on ranking diffusion models with various configurations, including architectures, quantization levels, and sampler schedules on COCO and DiffusionDB datasets. Our searched 50-item subset could achieve comparable evaluation quality to the randomly sampled 500-item subset for COCO annotations on unseen models, achieving a 10x evaluation speedup. We release the condensed subset of these commonly used datasets to help facilitate diffusion algorithm design and evaluation, and open-source FlashEval as a tool for condensing future datasets, accessible at https://github.com/thu-nics/FlashEval.
Abstract:Current deep learning reconstruction for accelerated cardiac cine MRI suffers from spatial and temporal blurring. We aim to improve image sharpness and motion delineation for cine MRI under high undersampling rates. A spatiotemporal diffusion enhancement model conditional on an existing deep learning reconstruction along with a novel paired sampling strategy was developed. The diffusion model provided sharper tissue boundaries and clearer motion than the original reconstruction in experts evaluation on clinical data. The innovative paired sampling strategy substantially reduced artificial noises in the generative results.
Abstract:The currently limited quality of accelerated cardiac cine reconstruction may potentially be improved by the emerging diffusion models, but the clinically unacceptable long processing time poses a challenge. We aim to develop a clinically feasible diffusion-model-based reconstruction pipeline to improve the image quality of cine MRI. A multi-in multi-out diffusion enhancement model together with fast inference strategies were developed to be used in conjunction with a reconstruction model. The diffusion reconstruction reduced spatial and temporal blurring in prospectively undersampled clinical data, as validated by experts inspection. The 1.5s per video processing time enabled the approach to be applied in clinical scenarios.
Abstract:In artificial intelligence (AI), especially deep learning, data diversity and volume play a pivotal role in model development. However, training a robust deep learning model often faces challenges due to data privacy, regulations, and the difficulty of sharing data between different locations, especially for medical applications. To address this, we developed a method called the Federated Data Model (FDM). This method uses diffusion models to learn the characteristics of data at one site and then creates synthetic data that can be used at another site without sharing the actual data. We tested this approach with a medical image segmentation task, focusing on cardiac magnetic resonance images from different hospitals. Our results show that models trained with this method perform well both on the data they were originally trained on and on data from other sites. This approach offers a promising way to train accurate and privacy-respecting AI models across different locations.
Abstract:In recent years, Large Language Models (LLMs) like ChatGPT have seen considerable advancements and have been applied in diverse fields. Built on the Transformer architecture, these models are trained on extensive datasets, enabling them to understand and generate human language effectively. In the financial domain, the deployment of LLMs is gaining momentum. These models are being utilized for automating financial report generation, forecasting market trends, analyzing investor sentiment, and offering personalized financial advice. Leveraging their natural language processing capabilities, LLMs can distill key insights from vast financial data, aiding institutions in making informed investment choices and enhancing both operational efficiency and customer satisfaction. In this study, we provide a comprehensive overview of the emerging integration of LLMs into various financial tasks. Additionally, we conducted holistic tests on multiple financial tasks through the combination of natural language instructions. Our findings show that GPT-4 effectively follow prompt instructions across various financial tasks. This survey and evaluation of LLMs in the financial domain aim to deepen the understanding of LLMs' current role in finance for both financial practitioners and LLM researchers, identify new research and application prospects, and highlight how these technologies can be leveraged to solve practical challenges in the finance industry.