论文检索

Reinforcement Learning

Ziniu Li, Tian Xu, Zeyu Qin, Yang Yu, Zhi-Quan Luo

Imitation learning (IL) algorithms excel in acquiring high-quality policies from expert data for sequential decision-making tasks. But, their effectiveness is hampered when faced with limited expert data. To tackle this challenge, a novel framework called (offline) IL with supplementary data has been proposed, which enhances learning by incorporating an additional yet imperfect dataset obtained inexpensively from sub-optimal policies. Nonetheless, learning becomes challenging due to the potential inclusion of out-of-expert-distribution samples. In this work, we propose a mathematical formalization of this framework, uncovering its limitations. Our theoretical analysis reveals that a naive approach—applying the behavioral cloning (BC) algorithm concept to the combined set of expert and supplementary data—may fall short of vanilla BC, which solely relies on expert data. This deficiency arises due to the distribution shift between the two data sources. To address this issue, we propose a new importance-sampling-based technique for selecting data within the expert distribution. We prove that the proposed method eliminates the gap of the naive approach, highlighting its efficacy when handling imperfect data. Empirical studies demonstrate that our method outperforms previous state-of-the-art methods in tasks including robotic locomotion control, Atari video games, and image classification. Overall, our work underscores the potential of improving IL by leveraging diverse data sources through effective data selection.

Applications/Everything Else

Ye Yuan, Can (Sam) Chen, Zixuan Liu, Willie Neiswanger, Xue (Steve) Liu

Offline model-based optimization aims to find a design that maximizes a property of interest using only an offline dataset, with applications in robot, protein, and molecule design, among others. A prevalent approach is gradient ascent, where a proxy model is trained on the offline dataset and then used to optimize the design. This method suffers from an out-of-distribution issue, where the proxy is not accurate for unseen designs. To mitigate this issue, we explore using a pseudo-labeler to generate valuable data for fine-tuning the proxy. Specifically, we propose $\textit{\textbf{I}mportance-aware \textbf{C}o-\textbf{T}eaching for Offline Model-based Optimization}~(\textbf{ICT})$. This method maintains three symmetric proxies with their mean ensemble as the final proxy, and comprises two steps. The first step is $\textit{pseudo-label-driven co-teaching}$. In this step, one proxy is iteratively selected as the pseudo-labeler for designs near the current optimization point, generating pseudo-labeled data. Subsequently, a co-teaching process identifies small-loss samples as valuable data and exchanges them between the other two proxies for fine-tuning, promoting knowledge transfer. This procedure is repeated three times, with a different proxy chosen as the pseudo-labeler each time, ultimately enhancing the ensemble performance.To further improve accuracy of pseudo-labels, we perform a secondary step of $\textit{meta-learning-based sample reweighting}$,which assigns importance weights to samples in the pseudo-labeled dataset and updates them via meta-learning. ICT achieves state-of-the-art results across multiple design-bench tasks, achieving the best mean rank $3.1$ and median rank $2$ among $15$ methods.Our source code can be accessed here.

Applications/Computer Vision

Haochen Wang, Junsong Fan, Yuxi Wang, Kaiyou Song, Tong Wang, ZHAO-XIANG ZHANG

As it is empirically observed that Vision Transformers (ViTs) are quite insensitive to the order of input tokens, the need for an appropriate self-supervised pretext task that enhances the location awareness of ViTs is becoming evident. To address this, we present DropPos, a novel pretext task designed to reconstruct Dropped Positions. The formulation of DropPos is simple: we first drop a large random subset of positional embeddings and then the model classifies the actual position for each non-overlapping patch among all possible positions solely based on their visual appearance. To avoid trivial solutions, we increase the difficulty of this task by keeping only a subset of patches visible. Additionally, considering there may be different patches with similar visual appearances, we propose position smoothing and attentive reconstruction strategies to relax this classification problem, since it is not necessary to reconstruct their exact positions in these cases. Empirical evaluations of DropPos show strong capabilities. DropPos outperforms supervised pre-training and achieves competitive results compared with state-of-the-art self-supervised alternatives on a wide range of downstream benchmarks. This suggests that explicitly encouraging spatial reasoning abilities, as DropPos does, indeed contributes to the improved location awareness of ViTs. The code is publicly available at https://github.com/Haochen-Wang409/DropPos.

Reinforcement Learning/Everything Else

Wei Fu, Weihua Du, Jingwei Li, Sunli Chen, Jingzhao Zhang, YI WU

In complex reinforcement learning (RL) problems, policies with similar rewards may have substantially different behaviors. It remains a fundamental challenge to optimize rewards while also discovering as many *diverse* strategies as possible, which can be crucial in many practical applications. Our study examines two design choices for tackling this challenge, i.e., *diversity measure* and *computation framework*. First, we find that with existing diversity measures, visually indistinguishable policies can still yield high diversity scores. To accurately capture the behavioral difference, we propose to incorporate the state-space distance information into the diversity measure. In addition, we examine two common computation frameworks for this problem, i.e., population-based training (PBT) and iterative learning (ITR). We show that although PBT is the precise problem formulation, ITR can achieve comparable diversity scores with higher computation efficiency, leading to improved solution quality in practice. Based on our analysis, we further combine ITR with two tractable realizations of the state-distance-based diversity measures and develop a novel diversity-driven RL algorithm, *State-based Intrinsic-reward Policy Optimization* (SIPO), with provable convergence properties. We empirically examine SIPO across three domains from robot locomotion to multi-agent games. In all of our testing environments, SIPO consistently produces strategically diverse and human-interpretable policies that cannot be discovered by existing baselines.

Reinforcement Learning/Deep RL

Sungho Choi, Seungyul Han, Woojun Kim, Jongseong Chae, Whiyoung Jung, Youngchul Sung

In this paper, we consider domain-adaptive imitation learning with visual observation, where an agent in a target domain learns to perform a task by observing expert demonstrations in a source domain. Domain adaptive imitation learning arises in practical scenarios where a robot, receiving visual sensory data, needs to mimic movements by visually observing other robots from different angles or observing robots of different shapes. To overcome the domain shift in cross-domain imitation learning with visual observation, we propose a novel framework for extracting domain-independent behavioral features from input observations that can be used to train the learner, based on dual feature extraction and image reconstruction. Empirical results demonstrate that our approach outperforms previous algorithms for imitation learning from visual observation with domain shift.

Applications/Robotics

Yao Mu, Qinglong Zhang, Mengkang Hu, Wenhai Wang, Mingyu Ding, Jun Jin, Bin Wang, Jifeng Dai, Yu Qiao, Ping Luo

Embodied AI is a crucial frontier in robotics, capable of planning and executing action sequences for robots to accomplish long-horizon tasks in physical environments.In this work, we introduce EmbodiedGPT, an end-to-end multi-modal foundation model for embodied AI, empowering embodied agents with multi-modal understanding and execution capabilities. To achieve this, we have made the following efforts: (i) We craft a large-scale embodied planning dataset, termed EgoCOT. The dataset consists of carefully selected videos from the Ego4D dataset, along with corresponding high-quality language instructions. Specifically, we generate a sequence of sub-goals with the "Chain of Thoughts" mode for effective embodied planning.(ii) We introduce an efficient training approach to EmbodiedGPT for high-quality plan generation, by adapting a 7B large language model (LLM) to the EgoCOT dataset via prefix tuning. (iii) We introduce a paradigm for extracting task-related features from LLM-generated planning queries to form a closed loop between high-level planning and low-level control.Extensive experiments show the effectiveness of EmbodiedGPT on embodied tasks, including embodied planning, embodied control, visual captioning, and visual question answering.Notably, EmbodiedGPT significantly enhances the success rate of the embodied control task by extracting more effective features. It has achieved a remarkable 1.6 times increase in success rate on the Franka Kitchen benchmark and a 1.3 times increase on the Meta-World benchmark, compared to the BLIP-2 baseline fine-tuned with the Ego4D dataset.

Miscellaneous Aspects of Machine Learning/Transfer, Multitask and Meta-learning

Deepali Jain, Krzysztof M Choromanski, Kumar Avinava Dubey, Sumeet Singh, Vikas Sindhwani, Tingnan Zhang, Jie Tan

In this work, we propose a new class of learnable optimizers, called Mnemosyne. It is based on the novel spatio-temporal low-rank implicit attention Transformers that can learn to train entire neural network architectures, including other Transformers, without any task-specific optimizer tuning. We show that Mnemosyne: (a) outperforms popular LSTM optimizers (also with new feature engineering to mitigate catastrophic forgetting of LSTMs), (b) can successfully train Transformers while using simple meta-training strategies that require minimal computational resources, (c) matches accuracy-wise SOTA hand-designed optimizers with carefully tuned hyper-parameters (often producing top performing models). Furthermore, Mnemosyne provides space complexity comparable to that of its hand-designed first-order counterparts, which allows it to scale to training larger sets of parameters. We conduct an extensive empirical evaluation of Mnemosyne on: (a) fine-tuning a wide range of Vision Transformers (ViTs) from medium-size architectures to massive ViT-Hs (36 layers, 16 heads), (b) pre-training BERT models and (c) soft prompt-tuning large 11B+ T5XXL models. We complement our results with a comprehensive theoretical analysis of the compact associative memory used by Mnemosyne which we believe was never done before.

Applications/Robotics

Hongxin Li, Jingran Su, Yuntao Chen, Qing Li, ZHAO-XIANG ZHANG

Computer end users have spent billions of hours completing daily tasks like tabular data processing and project timeline scheduling. Most of these tasks are repetitive and error-prone, yet most end users lack the skill to automate these burdensome works. With the advent of large language models (LLMs), directing software with natural language user requests become a reachable goal. In this work, we propose a SheetCopilot agent that takes natural language task and control spreadsheet to fulfill the requirements. We propose a set of atomic actions as an abstraction of spreadsheet software functionalities. We further design a state machine-based task planning framework for LLMs to robustly interact with spreadsheets. We curate a representative dataset containing 221 spreadsheet control tasks and establish a fully automated evaluation pipeline for rigorously benchmarking the ability of LLMs in software control tasks. Our SheetCopilot correctly completes 44.3\% of tasks for a single generation, outperforming the strong code generation baseline by a wide margin. Our project page: https://sheetcopilot.github.io/.

Reinforcement Learning/Multi-agent

Esmaeil Seraj, Jerry Xiong, Mariah Schrum, Matthew Gombolay

Extending recent advances in Learning from Demonstration (LfD) frameworks to multi-robot settings poses critical challenges such as environment non-stationarity due to partial observability which is detrimental to the applicability of existing methods. Although prior work has shown that enabling communication among agents of a robot team can alleviate such issues, creating inter-agent communication under existing Multi-Agent LfD (MA-LfD) frameworks requires the human expert to provide demonstrations for both environment actions and communication actions, which necessitates an efficient communication strategy on a known message spaces. To address this problem, we propose Mixed-Initiative Multi-Agent Apprenticeship Learning (MixTURE). MixTURE enables robot teams to learn from a human expert-generated data a preferred policy to accomplish a collaborative task, while simultaneously learning emergent inter-agent communication to enhance team coordination. The key ingredient to MixTURE's success is automatically learning a communication policy, enhanced by a mutual-information maximizing reverse model that rationalizes the underlying expert demonstrations without the need for human generated data or an auxiliary reward function. MixTURE outperforms a variety of relevant baselines on diverse data generated by human experts in complex heterogeneous domains. MixTURE is the first MA-LfD framework to enable learning multi-robot collaborative policies directly from real human data, resulting in ~44% less human workload, and ~46% higher usability score.

Applications/Robotics

Tianhao Wu, Mingdong Wu, Jiyao Zhang, Yunchong Gan, Hao Dong

The use of anthropomorphic robotic hands for assisting individuals in situations where human hands may be unavailable or unsuitable has gained significant importance. In this paper, we propose a novel task called human-assisting dexterous grasping that aims to train a policy for controlling a robotic hand's fingers to assist users in grasping objects. Unlike conventional dexterous grasping, this task presents a more complex challenge as the policy needs to adapt to diverse user intentions, in addition to the object's geometry. We address this challenge by proposing an approach consisting of two sub-modules: a hand-object-conditional grasping primitive called Grasping Gradient Field (GraspGF), and a history-conditional residual policy. GraspGF learns 'how' to grasp by estimating the gradient of a synthesised success grasping example set, while the residual policy determines 'when' and at what speed the grasping action should be executed based on the trajectory history. Experimental results demonstrate the superiority of our proposed method compared to baselines, highlighting the user-awareness and practicality in real-world applications. The codes and demonstrations can be viewed at https://sites.google.com/view/graspgf.

Applications/Computer Vision

Zihui (Sherry) Xue, Kristen Grauman

The egocentric and exocentric viewpoints of a human activity look dramatically different, yet invariant representations to link them are essential for many potential applications in robotics and augmented reality. Prior work is limited to learning view-invariant features from paired synchronized viewpoints. We relax that strong data assumption and propose to learn fine-grained action features that are invariant to the viewpoints by aligning egocentric and exocentric videos in time, even when not captured simultaneously or in the same environment. To this end, we propose AE2, a self-supervised embedding approach with two key designs: (1) an object-centric encoder that explicitly focuses on regions corresponding to hands and active objects; (2) a contrastive-based alignment objective that leverages temporally reversed frames as negative samples. For evaluation, we establish a benchmark for fine-grained video understanding in the ego-exo context, comprising four datasets---including an ego tennis forehand dataset we collected, along with dense per-frame labels we annotated for each dataset. On the four datasets, our AE2 method strongly outperforms prior work in a variety of fine-grained downstream tasks, both in regular and cross-view settings.

Reinforcement Learning

Shutong Ding, Jingya Wang, Yali Du, Ye Shi

Recent advances in constrained reinforcement learning (RL) have endowed reinforcement learning with certain safety guarantees. However, deploying existing constrained RL algorithms in continuous control tasks with general hard constraints remains challenging, particularly in those situations with non-convex hard constraints. Inspired by the generalized reduced gradient (GRG) algorithm, a classical constrained optimization technique, we propose a reduced policy optimization (RPO) algorithm that combines RL with GRG to address general hard constraints. RPO partitions actions into basic actions and nonbasic actions following the GRG method and outputs the basic actions via a policy network. Subsequently, RPO calculates the nonbasic actions by solving equations based on equality constraints using the obtained basic actions. The policy network is then updated by implicitly differentiating nonbasic actions with respect to basic actions. Additionally, we introduce an action projection procedure based on the reduced gradient and apply a modified Lagrangian relaxation technique to ensure inequality constraints are satisfied. To the best of our knowledge, RPO is the first attempt that introduces GRG to RL as a way of efficiently handling both equality and inequality hard constraints. It is worth noting that there is currently a lack of RL environments with complex hard constraints, which motivates us to develop three new benchmarks: two robotics manipulation tasks and a smart grid operation control task. With these benchmarks, RPO achieves better performance than previous constrained RL algorithms in terms of both cumulative reward and constraint violation. We believe RPO, along with the new benchmarks, will open up new opportunities for applying RL to real-world problems with complex constraints.

Applications/Robotics

Keji He, Chenyang Si, Zhihe Lu, Yan Huang, Liang Wang, Xinchao Wang

Vision-and-Language Navigation (VLN) is a challenging task that requires an agent to navigate through complex environments based on natural language instructions. In contrast to conventional approaches, which primarily focus on the spatial domain exploration, we propose a paradigm shift toward the Fourier domain. This alternative perspective aims to enhance visual-textual matching, ultimately improving the agent's ability to understand and execute navigation tasks based on the given instructions. In this study, we first explore the significance of high-frequency information in VLN and provide evidence that it is instrumental in bolstering visual-textual matching processes. Building upon this insight, we further propose a sophisticated and versatile Frequency-enhanced Data Augmentation (FDA) technique to improve the VLN model's capability of capturing critical high-frequency information. Specifically, this approach requires the agent to navigate in environments where only a subset of high-frequency visual information corresponds with the provided textual instructions, ultimately fostering the agent's ability to selectively discern and capture pertinent high-frequency features according to the given instructions. Promising results on R2R, RxR, CVDN and REVERIE demonstrate that our FDA can be readily integrated with existing VLN approaches, improving performance without adding extra parameters, and keeping models simple and efficient. The code is available at https://github.com/hekj/FDA.

Reinforcement Learning/Average Cost Reward

Nuoya Xiong, Yihan Du, Longbo Huang

We investigate a novel safe reinforcement learning problem with step-wise violation constraints. Our problem differs from existing works in that we focus on stricter step-wise violation constraints and do not assume the existence of safe actions, making our formulation more suitable for safety-critical applications that need to ensure safety in all decision steps but may not always possess safe actions, e.g., robot control and autonomous driving.We propose an efficient algorithm SUCBVI, which guarantees $\widetilde{\mathcal{O}}(\sqrt{ST})$ or gap-dependent $\widetilde{\mathcal{O}}(S/\mathcal{C}_{\mathrm{gap}} + S^2AH^2)$ step-wise violation and $\widetilde{\mathcal{O}}(\sqrt{H^3SAT})$ regret. Lower bounds are provided to validate the optimality in both violation and regret performance with respect to the number of states $S$ and the total number of steps $T$. Moreover, we further study an innovative safe reward-free exploration problem with step-wise violation constraints. For this problem, we design algorithm SRF-UCRL to find a near-optimal safe policy, which achieves nearly state-of-the-art sample complexity $\widetilde{\mathcal{O}}((\frac{S^2AH^2}{\varepsilon}+\frac{H^4SA}{\varepsilon^2})(\log(\frac{1}{\delta})+S))$, and guarantees $\widetilde{\mathcal{O}}(\sqrt{ST})$ violation during exploration. Experimental results demonstrate the superiority of our algorithms in safety performance and corroborate our theoretical results.

Applications/Computer Vision

Ava Pun, Gary Sun, Jingkang Wang, Yun Chen, Ze Yang, Sivabalan Manivasagam, Wei-Chiu Ma, Raquel Urtasun

Different outdoor illumination conditions drastically alter the appearance of urban scenes, and they can harm the performance of image-based robot perception systems if not seen during training. Camera simulation provides a cost-effective solution to create a large dataset of images captured under different lighting conditions. Towards this goal, we propose LightSim, a neural lighting camera simulation system that enables diverse, realistic, and controllable data generation. LightSim automatically builds lighting-aware digital twins at scale from collected raw sensor data and decomposes the scene into dynamic actors and static background with accurate geometry, appearance, and estimated scene lighting. These digital twins enable actor insertion, modification, removal, and rendering from a new viewpoint, all in a lighting-aware manner. LightSim then combines physically-based and learnable deferred rendering to perform realistic relighting of modified scenes, such as altering the sun location and modifying the shadows or changing the sun brightness, producing spatially- and temporally-consistent camera videos. Our experiments show that LightSim generates more realistic relighting results than prior work. Importantly, training perception models on data generated by LightSim can significantly improve their performance. Our project page is available at https://waabi.ai/lightsim/.

Deep Learning/Generative Models and Autoencoders

Andy Shih, Suneel Belkhale, Stefano Ermon, Dorsa Sadigh, Nima Anari

Diffusion models are powerful generative models but suffer from slow sampling, often taking 1000 sequential denoising steps for one sample. As a result, considerable efforts have been directed toward reducing the number of denoising steps, but these methods hurt sample quality. Instead of reducing the number of denoising steps (trading quality for speed), in this paper we explore an orthogonal approach: can we run the denoising steps in parallel (trading compute for speed)? In spite of the sequential nature of the denoising steps, we show that surprisingly it is possible to parallelize sampling via Picard iterations, by guessing the solution of future denoising steps and iteratively refining until convergence. With this insight, we present ParaDiGMS, a novel method to accelerate the sampling of pretrained diffusion models by denoising multiple steps in parallel. ParaDiGMS is the first diffusion sampling method that enables trading compute for speed and is even compatible with existing fast sampling techniques such as DDIM and DPMSolver. Using ParaDiGMS, we improve sampling speed by 2-4x across a range of robotics and image generation models, giving state-of-the-art sampling speeds of 0.2s on 100-step DiffusionPolicy and 14.6s on 1000-step StableDiffusion-v2 with no measurable degradation of task reward, FID score, or CLIP score.

Applications/Robotics

Tsun-Hsuan Johnson Wang, Juntian Zheng, Pingchuan Ma, Yilun Du, Byungchul Kim, Andrew Spielberg, Josh Tenenbaum, Chuang Gan, Daniela Rus

Nature evolves creatures with a high complexity of morphological and behavioral intelligence, meanwhile computational methods lag in approaching that diversity and efficacy. Co-optimization of artificial creatures' morphology and control in silico shows promise for applications in physical soft robotics and virtual character creation; such approaches, however, require developing new learning algorithms that can reason about function atop pure structure. In this paper, we present DiffuseBot, a physics-augmented diffusion model that generates soft robot morphologies capable of excelling in a wide spectrum of tasks. \name bridges the gap between virtually generated content and physical utility by (i) augmenting the diffusion process with a physical dynamical simulation which provides a certificate of performance, and (ii) introducing a co-design procedure that jointly optimizes physical design and control by leveraging information about physical sensitivities from differentiable simulation. We showcase a range of simulated and fabricated robots along with their capabilities. Check our website: https://diffusebot.github.io/

Reinforcement Learning

Marcel Torne Villasevil, Max Balsells I Pamies, Zihan Wang, Samedh Desai, Tao Chen, Pulkit Agrawal, Abhishek Gupta

Exploration and reward specification are fundamental and intertwined challenges for reinforcement learning. Solving sequential decision making tasks with a non-trivial element of exploration requires either specifying carefully designed reward functions or relying on indiscriminate, novelty seeking exploration bonuses. Human supervisors can provide effective guidance in the loop to direct the exploration process, but prior methods to leverage this guidance require constant synchronous high-quality human feedback, which is expensive and impractical to obtain. In this work, we propose a technique - Human Guided Exploration (HUGE), that is able to leverage low-quality feedback from non-expert users, which is infrequent, asynchronous and noisy, to guide exploration for reinforcement learning, without requiring careful reward specification. The key idea is to separate the challenges of directed exploration and policy learning - human feedback is used to direct exploration, while self-supervised policy learning is used to independently learn unbiased behaviors from the collected data. We show that this procedure can leverage noisy, asynchronous human feedback to learn tasks with no hand-crafted reward design or exploration bonuses. We show that HUGE is able to learn a variety of challenging multi-stage robotic navigation and manipulation tasks in simulation using crowdsourced feedback from non-expert users. Moreover, this paradigm can be scaled to learning directly on real-world robots.

Theory/Game Theory

Denizalp Goktas, Arjun Prakash, Amy Greenwald

Zero-sum Markov Stackelberg games can be used to model myriad problems, in domains ranging from economics to human robot interaction. In this paper, we develop policy gradient methods that solve these games in continuous state and action settings using noisy gradient estimates computed from observed trajectories of play. When the games are convex-concave, we prove that our algorithms converge to Stackelberg equilibrium in polynomial time. We also show that reach-avoid problems are naturally modeled as convex-concave zero-sum Markov Stackelberg games, and that Stackelberg equilibrium policies are more effective than their Nash counterparts in these problems.

Probabilistic Methods/Monte Carlo and Sampling Methods

Isaac Reid, Krzysztof M Choromanski, Adrian Weller

We present a novel mechanism to improve the accuracy of the recently-introduced class of graph random features (GRFs). Our method induces negative correlations between the lengths of the algorithm's random walks by imposing antithetic termination: a procedure to sample more diverse random walks which may be of independent interest. It has a trivial drop-in implementation. We derive strong theoretical guarantees on the properties of these quasi-Monte Carlo GRFs (q-GRFs), proving that they yield lower-variance estimators of the $2$-regularised Laplacian kernel under mild conditions. Remarkably, our results hold for any graph topology. We demonstrate empirical accuracy improvements on a variety of tasks including a new practical application: time-efficient approximation of the graph diffusion process. To our knowledge, q-GRFs constitute the first rigorously studied quasi-Monte Carlo scheme for kernels defined on combinatorial objects, inviting new research on correlations between graph random walks.