Reinforcement Learning Gradients as Vitamin for Online Finetuning Decision Transformers

Decision Transformers have recently emerged as a new and compelling paradigm for offline Reinforcement Learning (RL), completing a trajectory in an autoregressive way. While improvements have been made to overcome initial shortcomings, online finetuning of decision transformers has been surprisingly under-explored. The widely adopted state-of-the-art Online Decision Transformer (ODT) still struggles when pretrained with low-reward offline data. In this paper, we theoretically analyze the online-finetuning of the decision transformer, showing that the commonly used Return-To-Go (RTG) that's far from the expected return hampers the online fine-tuning process. This problem, however, is well-addressed by the value function and advantage of standard RL algorithms. As suggested by our analysis, in our experiments, we hence find that simply adding TD3 gradients to the finetuning process of ODT effectively improves the online finetuning performance of ODT, especially if ODT is pretrained with low-reward offline data. These findings provide new directions to further improve decision transformers.

Natural Adversarial Patch Generation Method Based on Latent Diffusion Model

Recently, some research show that deep neural networks are vulnerable to the adversarial attacks, the well-trainned samples or patches could be used to trick the neural network detector or human visual perception. However, these adversarial patches, with their conspicuous and unusual patterns, lack camouflage and can easily raise suspicion in the real world. To solve this problem, this paper proposed a novel adversarial patch method called the Latent Diffusion Patch (LDP), in which, a pretrained encoder is first designed to compress the natural images into a feature space with key characteristics. Then trains the diffusion model using the above feature space. Finally, explore the latent space of the pretrained diffusion model using the image denoising technology. It polishes the patches and images through the powerful natural abilities of diffusion models, making them more acceptable to the human visual system. Experimental results, both digital and physical worlds, show that LDPs achieve a visual subjectivity score of 87.3%, while still maintaining effective attack capabilities.

Open-sourced Data Ecosystem in Autonomous Driving: the Present and Future

With the continuous maturation and application of autonomous driving technology, a systematic examination of open-source autonomous driving datasets becomes instrumental in fostering the robust evolution of the industry ecosystem. Current autonomous driving datasets can broadly be categorized into two generations. The first-generation autonomous driving datasets are characterized by relatively simpler sensor modalities, smaller data scale, and is limited to perception-level tasks. KITTI, introduced in 2012, serves as a prominent representative of this initial wave. In contrast, the second-generation datasets exhibit heightened complexity in sensor modalities, greater data scale and diversity, and an expansion of tasks from perception to encompass prediction and control. Leading examples of the second generation include nuScenes and Waymo, introduced around 2019. This comprehensive review, conducted in collaboration with esteemed colleagues from both academia and industry, systematically assesses over seventy open-source autonomous driving datasets from domestic and international sources. It offers insights into various aspects, such as the principles underlying the creation of high-quality datasets, the pivotal role of data engine systems, and the utilization of generative foundation models to facilitate scalable data generation. Furthermore, this review undertakes an exhaustive analysis and discourse regarding the characteristics and data scales that future third-generation autonomous driving datasets should possess. It also delves into the scientific and technical challenges that warrant resolution. These endeavors are pivotal in advancing autonomous innovation and fostering technological enhancement in critical domains. For further details, please refer to https://github.com/OpenDriveLab/DriveAGI.

Offline Imitation from Observation via Primal Wasserstein State Occupancy Matching

In real-world scenarios, arbitrary interactions with the environment can often be costly, and actions of expert demonstrations are not always available. To reduce the need for both, Offline Learning from Observations (LfO) is extensively studied, where the agent learns to solve a task with only expert states and \textit{task-agnostic} non-expert state-action pairs. The state-of-the-art DIstribution Correction Estimation (DICE) methods minimize the state occupancy divergence between the learner and expert policies. However, they are limited to either $f$-divergences (KL and $\chi^2$) or Wasserstein distance with Rubinstein duality, the latter of which constrains the underlying distance metric crucial to the performance of Wasserstein-based solutions. To address this problem, we propose Primal Wasserstein DICE (PW-DICE), which minimizes the primal Wasserstein distance between the expert and learner state occupancies with a pessimistic regularizer and leverages a contrastively learned distance as the underlying metric for the Wasserstein distance. Theoretically, we prove that our framework is a generalization of the state-of-the-art, SMODICE, and unifies $f$-divergence and Wasserstein minimization. Empirically, we find that PW-DICE improves upon several state-of-the-art methods on multiple testbeds.

A Simple Solution for Offline Imitation from Observations and Examples with Possibly Incomplete Trajectories

Offline imitation from observations aims to solve MDPs where only task-specific expert states and task-agnostic non-expert state-action pairs are available. Offline imitation is useful in real-world scenarios where arbitrary interactions are costly and expert actions are unavailable. The state-of-the-art "DIstribution Correction Estimation" (DICE) methods minimize divergence of state occupancy between expert and learner policies and retrieve a policy with weighted behavior cloning; however, their results are unstable when learning from incomplete trajectories, due to a non-robust optimization in the dual domain. To address the issue, in this paper, we propose Trajectory-Aware Imitation Learning from Observations (TAILO). TAILO uses a discounted sum along the future trajectory as the weight for weighted behavior cloning. The terms for the sum are scaled by the output of a discriminator, which aims to identify expert states. Despite simplicity, TAILO works well if there exist trajectories or segments of expert behavior in the task-agnostic data, a common assumption in prior work. In experiments across multiple testbeds, we find TAILO to be more robust and effective, particularly with incomplete trajectories.

Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models

While large language models (LLMs) have demonstrated impressive performance on a range of decision-making tasks, they rely on simple acting processes and fall short of broad deployment as autonomous agents. We introduce LATS (Language Agent Tree Search), a general framework that synergizes the capabilities of LLMs in planning, acting, and reasoning. Drawing inspiration from Monte Carlo tree search in model-based reinforcement learning, LATS employs LLMs as agents, value functions, and optimizers, repurposing their latent strengths for enhanced decision-making. What is crucial in this method is the use of an environment for external feedback, which offers a more deliberate and adaptive problem-solving mechanism that moves beyond the limitations of existing techniques. Our experimental evaluation across diverse domains, such as programming, HotPotQA, and WebShop, illustrates the applicability of LATS for both reasoning and acting. In particular, LATS achieves 94.4\% for programming on HumanEval with GPT-4 and an average score of 75.9 for web browsing on WebShop with GPT-3.5, demonstrating the effectiveness and generality of our method.

PSDR-Room: Single Photo to Scene using Differentiable Rendering

A 3D digital scene contains many components: lights, materials and geometries, interacting to reach the desired appearance. Staging such a scene is time-consuming and requires both artistic and technical skills. In this work, we propose PSDR-Room, a system allowing to optimize lighting as well as the pose and materials of individual objects to match a target image of a room scene, with minimal user input. To this end, we leverage a recent path-space differentiable rendering approach that provides unbiased gradients of the rendering with respect to geometry, lighting, and procedural materials, allowing us to optimize all of these components using gradient descent to visually match the input photo appearance. We use recent single-image scene understanding methods to initialize the optimization and search for appropriate 3D models and materials. We evaluate our method on real photographs of indoor scenes and demonstrate the editability of the resulting scene components.

Neural-PBIR Reconstruction of Shape, Material, and Illumination

Reconstructing the shape and spatially varying surface appearances of a physical-world object as well as its surrounding illumination based on 2D images (e.g., photographs) of the object has been a long-standing problem in computer vision and graphics. In this paper, we introduce a robust object reconstruction pipeline combining neural based object reconstruction and physics-based inverse rendering (PBIR). Specifically, our pipeline firstly leverages a neural stage to produce high-quality but potentially imperfect predictions of object shape, reflectance, and illumination. Then, in the later stage, initialized by the neural predictions, we perform PBIR to refine the initial results and obtain the final high-quality reconstruction. Experimental results demonstrate our pipeline significantly outperforms existing reconstruction methods quality-wise and performance-wise.

CEIP: Combining Explicit and Implicit Priors for Reinforcement Learning with Demonstrations

Although reinforcement learning has found widespread use in dense reward settings, training autonomous agents with sparse rewards remains challenging. To address this difficulty, prior work has shown promising results when using not only task-specific demonstrations but also task-agnostic albeit somewhat related demonstrations. In most cases, the available demonstrations are distilled into an implicit prior, commonly represented via a single deep net. Explicit priors in the form of a database that can be queried have also been shown to lead to encouraging results. To better benefit from available demonstrations, we develop a method to Combine Explicit and Implicit Priors (CEIP). CEIP exploits multiple implicit priors in the form of normalizing flows in parallel to form a single complex prior. Moreover, CEIP uses an effective explicit retrieval and push-forward mechanism to condition the implicit priors. In three challenging environments, we find the proposed CEIP method to improve upon sophisticated state-of-the-art techniques.

Improving the estimation of directional area scattering factor (DASF) from canopy reflectance: theoretical basis and validation

Directional area scattering factor (DASF) is a critical canopy structural parameter for vegetation monitoring. It provides an efficient tool for decoupling of canopy structure and leaf optics from canopy reflectance. Current standard approach to estimate DASF from canopy bidirectional reflectance factor (BRF) is based on the assumption that in the weakly absorbing 710 to 790 nm spectral interval, leaf scattering does not change much with the concentration of dry matter and thus its variation can be neglected. This results in biased estimates of DASF and consequently leads to uncertainty in DASF-related applications. This study proposes a new approach to account for variations in concentrations of this biochemical constituent, which additionally uses the canopy BRF at 2260 nm. In silico analysis of the proposed approach suggests significant increase in accuracy over the standard technique by a relative root mean square error (rRMSE) of 49% and 34% for one- and three dimensional scenes, respectively. When compared with indoor multi-angular hyperspectral measurements reported in literature, the mean absolute error has reduced by 68% for needle leaf and 20% for broadleaf canopies. Thus, the proposed DASF estimation approach outperforms the current one and can be used more reliably in DASF-related applications, such as vegetation monitoring of functional traits, dynamics, and radiation budget.