论文检索

Applications/Robotics

Ziang Liu, Genggeng Zhou, Jeff He, Tobia Marcucci, Fei-Fei Li, Jiajun Wu, Yunzhu Li

Learning predictive models from observations using deep neural networks (DNNs) is a promising new approach to many real-world planning and control problems. However, common DNNs are too unstructured for effective planning, and current control methods typically rely on extensive sampling or local gradient descent. In this paper, we propose a new framework for integrated model learning and predictive control that is amenable to efficient optimization algorithms. Specifically, we start with a ReLU neural model of the system dynamics and, with minimal losses in prediction accuracy, we gradually sparsify it by removing redundant neurons. This discrete sparsification process is approximated as a continuous problem, enabling an end-to-end optimization of both the model architecture and the weight parameters. The sparsified model is subsequently used by a mixed-integer predictive controller, which represents the neuron activations as binary variables and employs efficient branch-and-bound algorithms. Our framework is applicable to a wide variety of DNNs, from simple multilayer perceptrons to complex graph neural dynamics. It can efficiently handle tasks involving complicated contact dynamics, such as object pushing, compositional object sorting, and manipulation of deformable objects. Numerical and hardware experiments show that, despite the aggressive sparsification, our framework can deliver better closed-loop performance than existing state-of-the-art methods.

Reinforcement Learning/Deep RL

Michael Beukman, Devon Jarvis, Richard Klein, Steven James, Benjamin Rosman

While reinforcement learning has achieved remarkable successes in several domains, its real-world application is limited due to many methods failing to generalise to unfamiliar conditions. In this work, we consider the problem of generalising to new transition dynamics, corresponding to cases in which the environment's response to the agent's actions differs. For example, the gravitational force exerted on a robot depends on its mass and changes the robot's mobility. Consequently, in such cases, it is necessary to condition an agent's actions on extrinsic state information and pertinent contextual information reflecting how the environment responds. While the need for context-sensitive policies has been established, the manner in which context is incorporated architecturally has received less attention. Thus, in this work, we present an investigation into how context information should be incorporated into behaviour learning to improve generalisation. To this end, we introduce a neural network architecture, the Decision Adapter, which generates the weights of an adapter module and conditions the behaviour of an agent on the context information. We show that the Decision Adapter is a useful generalisation of a previously proposed architecture and empirically demonstrate that it results in superior generalisation performance compared to previous approaches in several environments. Beyond this, the Decision Adapter is more robust to irrelevant distractor variables than several alternative methods.

Probabilistic Methods/Monte Carlo and Sampling Methods

Ali Younis, Erik Sudderth

Particle filters flexibly represent multiple posterior modes nonparametrically, via a collection of weighted samples, but have classically been applied to tracking problems with known dynamics and observation likelihoods. Such generative models may be inaccurate or unavailable for high-dimensional observations like images. We instead leverage training data to discriminatively learn particle-based representations of uncertainty in latent object states, conditioned on arbitrary observations via deep neural network encoders. While prior discriminative particle filters have used heuristic relaxations of discrete particle resampling, or biased learning by truncating gradients at resampling steps, we achieve unbiased and low-variance gradient estimates by representing posteriors as continuous mixture densities. Our theory and experiments expose dramatic failures of existing reparameterization-based estimators for mixture gradients, an issue we address via an importance-sampling gradient estimator. Unlike standard recurrent neural networks, our mixture density particle filter represents multimodal uncertainty in continuous latent states, improving accuracy and robustness. On a range of challenging tracking and robot localization problems, our approach achieves dramatic improvements in accuracy, will also showing much greater stability across multiple training runs.

Applications/Robotics

Wenlong Huang, Fei Xia, Dhruv Shah, Danny Driess, Andy Zeng, Yao Lu, Pete Florence, Igor Mordatch, Sergey Levine, Karol Hausman 等

Recent progress in large language models (LLMs) has demonstrated the ability to learn and leverage Internet-scale knowledge through pre-training with autoregressive models. Unfortunately, applying such models to settings with embodied agents, such as robots, is challenging due to their lack of experience with the physical world, inability to parse non-language observations, and ignorance of rewards or safety constraints that robots may require. On the other hand, language-conditioned robotic policies that learn from interaction data can provide the necessary grounding that allows the agent to be correctly situated in the real world, but such policies are limited by the lack of high-level semantic understanding due to the limited breadth of the interaction data available for training them. Thus, if we want to make use of the semantic knowledge in a language model while still situating it in an embodied setting, we must construct an action sequence that is both likely according to the language model and also realizable according to grounded models of the environment. We frame this as a problem similar to probabilistic filtering: decode a sequence that both has high probability under the language model and high probability under a set of grounded model objectives. We demonstrate how such grounded models can be obtained across three simulation and real-world domains, and that the proposed decoding strategy is able to solve complex, long-horizon embodiment tasks in a robotic setting by leveraging the knowledge of both models.

Reinforcement Learning/Deep RL

Siming Lan, Rui Zhang, Qi Yi, Jiaming Guo, Shaohui Peng, Yunkai Gao, Fan Wu, Ruizhi Chen, Zidong Du, Xing Hu 等

In the field of multi-task reinforcement learning, the modular principle, which involves specializing functionalities into different modules and combining them appropriately, has been widely adopted as a promising approach to prevent the negative transfer problem that performance degradation due to conflicts between tasks. However, most of the existing multi-task RL methods only combine shared modules at the task level, ignoring that there may be conflicts within the task. In addition, these methods do not take into account that without constraints, some modules may learn similar functions, resulting in restricting the model's expressiveness and generalization capability of modular methods.In this paper, we propose the Contrastive Modules with Temporal Attention(CMTA) method to address these limitations. CMTA constrains the modules to be different from each other by contrastive learning and combining shared modules at a finer granularity than the task level with temporal attention, alleviating the negative transfer within the task and improving the generalization ability and the performance for multi-task RL.We conducted the experiment on Meta-World, a multi-task RL benchmark containing various robotics manipulation tasks. Experimental results show that CMTA outperforms learning each task individually for the first time and achieves substantial performance improvements over the baselines.

Reinforcement Learning/Planning

Siyuan Zhou, Yilun Du, Shun Zhang, Mengdi Xu, Yikang Shen, Wei Xiao, Dit-Yan Yeung, Chuang Gan

Diffusion models have risen a promising approach to data-driven planning, and have demonstrated impressive robotic control, reinforcement learning, and video planning performance. Given an effective planner, an important question to consider is replanning -- when given plans should be regenerated due to both action execution error and external environment changes. Direct plan execution, without replanning, is problematic as errors from individual actions rapidly accumulate and environments are partially observable and stochastic. Simultaneously, replanning at each timestep incurs a substantial computational cost, and may prevent successful task execution, as different generated plans prevent consistent progress to any particular goal. In this paper, we explore how we may effectively replan with diffusion models. We propose a principled approach to determine when to replan, based on the diffusion model's estimated likelihood of existing generated plans. We further present an approach to replan existing trajectories to ensure that new plans follow the same goal state as the original trajectory, which may efficiently bootstrap off previously generated plans. We illustrate how a combination of our proposed additions significantly improves the performance of diffusion planners leading to 38\% gains over past diffusion planning approaches on Maze2D and further enables handling of stochastic and long-horizon robotic control tasks.

Applications/Robotics

Arjun Majumdar, Karmesh Yadav, Sergio Arnaud, Jason Ma, Claire Chen, Sneha Silwal, Aryan Jain, Vincent-Pierre Berges, Tingfan Wu, Jay Vakil 等

We present the largest and most comprehensive empirical study of pre-trained visual representations (PVRs) or visual ‘foundation models’ for Embodied AI. First, we curate CortexBench, consisting of 17 different tasks spanning locomotion, navigation, dexterous, and mobile manipulation. Next, we systematically evaluate existing PVRs and find that none are universally dominant. To study the effect of pre-training data size and diversity, we combine over 4,000 hours of egocentric videos from 7 different sources (over 4.3M images) and ImageNet to train different-sized vision transformers using Masked Auto-Encoding (MAE) on slices of this data. Contrary to inferences from prior work, we find that scaling dataset size and diversity does not improve performance universally (but does so on average). Our largest model, named VC-1, outperforms all prior PVRs on average but does not universally dominate either. Next, we show that task- or domain-specific adaptation of VC-1 leads to substantial gains, with VC-1 (adapted) achieving competitive or superior performance than the best known results on all of the benchmarks in CortexBench. Finally, we present real-world hardware experiments, in which VC-1 and VC-1 (adapted) outperform the strongest pre-existing PVR. Overall, this paper presents no new techniques but a rigorous systematic evaluation, a broad set of findings about PVRs (that in some cases, refute those made in narrow domains in prior work), and open-sourced code and models (that required over 10,000 GPU-hours to train) for the benefit of the research community.

Theory/Game Theory

Siddharth Prasad, Maria-Florina Balcan, Tuomas Sandholm

We develop a versatile new methodology for multidimensional mechanism design that incorporates side information about agent types to generate high social welfare and high revenue simultaneously. Prominent sources of side information in practice include predictions from a machine-learning model trained on historical agent data, advice from domain experts, and even the mechanism designer's own gut instinct. In this paper we adopt a prior-free perspective that makes no assumptions on the correctness, accuracy, or source of the side information. First, we design a meta-mechanism that integrates input side information with an improvement of the classical VCG mechanism. The welfare, revenue, and incentive properties of our meta-mechanism are characterized by novel constructions we introduce based on the notion of a weakest competitor, which is an agent that has the smallest impact on welfare. We show that our meta-mechanism, when carefully instantiated, simultaneously achieves strong welfare and revenue guarantees parameterized by errors in the side information. When the side information is highly informative and accurate, our mechanism achieves welfare and revenue competitive with the total social surplus, and its performance decays continuously and gradually as the quality of the side information decreases. Finally, we apply our meta-mechanism to a setting where each agent's type is determined by a constant number of parameters. Specifically, agent types lie on constant-dimensional subspaces (of the potentially high-dimensional ambient type space) that are known to the mechanism designer. We use our meta-mechanism to obtain the first known welfare and revenue guarantees in this setting.

Reinforcement Learning/Planning

Edward Kim, Yohan Karunanayake, Hanna Kurniawati

Making good decisions in partially observable and non-deterministic scenarios is a crucial capability for robots. A Partially Observable Markov Decision Process (POMDP) is a general framework for the above problem. Despite advances in POMDP solving, problems with long planning horizons and evolving environments remain difficult to solve even by the best approximate solvers today. To alleviate this difficulty, we propose a slightly modified POMDP problem, called a Reference-Based POMDP, where the objective is to balance between maximizing the expected total reward and being close to a given reference (stochastic) policy. The optimal policy of a Reference-Based POMDP can be computed via iterative expectations using the given reference policy, thereby avoiding exhaustive enumeration of actions at each belief node of the search tree. We demonstrate theoretically that the standard POMDP under stochastic policies is related to the Reference-Based POMDP. To demonstrate the feasibility of exploiting the formulation, we present a basic algorithm RefSolver. Results from experiments on long-horizon navigation problems indicate that this basic algorithm substantially outperforms POMCP.

Applications/Language, Speech and Dialog

Heng Wang, Shangbin Feng, Tianxing He, Zhaoxuan Tan, Xiaochuang Han, Yulia Tsvetkov

Large language models (LLMs) are increasingly adopted for a variety of tasks with implicit graphical structures, such as planning in robotics, multi-hop question answering or knowledge probing, structured commonsense reasoning, and more. While LLMs have advanced the state-of-the-art on these tasks with structure implications, whether LLMs could explicitly process textual descriptions of graphs and structures, map them to grounded conceptual spaces, and perform structured operations remains underexplored. To this end, we propose NLGraph (Natural Language Graph), a comprehensive benchmark of graph-based problem solving designed in natural language. NLGraph contains 29,370 problems, covering eight graph reasoning tasks with varying complexity from simple tasks such as connectivity and shortest path up to complex problems such as maximum flow and simulating graph neural networks. We evaluate LLMs (GPT-3/4) with various prompting approaches on the NLGraph benchmark and find that 1) language models do demonstrate preliminary graph reasoning abilities, 2) the benefit of advanced prompting and in-context learning diminishes on more complex graph problems, while 3) LLMs are also (un)surprisingly brittle in the face of spurious correlations in graph and problem settings. We then propose Build-a-Graph Prompting and Algorithmic Prompting, two instruction-based approaches to enhance LLMs in solving natural language graph problems. Build-a-Graph and Algorithmic prompting improve the performance of LLMs on NLGraph by 3.07% to 16.85% across multiple tasks and settings, while how to solve the most complicated graph reasoning tasks in our setup with language models remains an open research question.

Applications/Robotics

Yongbo Chen, Hanna Kurniawati

Efficiently searching for target objects in complex environments that contain various types of furniture, such as shelves, tables, and beds, is crucial for mobile robots, but it poses significant challenges due to various factors such as localization errors, limited field of view, and visual occlusion. To address this problem, we propose a Partially Observable Markov Decision Process (POMDP) formulation with a growing state space for object search in a 3D region. We solve this POMDP by carefully designing a perception module and developing a planning algorithm, called Growing Partially Observable Monte-Carlo Planning (GPOMCP), based on online Monte-Carlo tree search and belief tree reuse with a novel upper confidence bound. We have demonstrated that belief tree reuse is reasonable and achieves good performance when the belief differences are limited. Additionally, we introduce a guessed target object with an updating grid world to guide the search in the information-less and reward-less cases, like the absence of any detected objects. We tested our approach using Gazebo simulations on four scenarios of target finding in a realistic indoor living environment with the Fetch robot simulator. Compared to the baseline approaches, which are based on POMCP, our results indicate that our approach enables the robot to find the target object with a higher success rate faster while using the same computational requirements.

Deep Learning/Generative Models and Autoencoders

Yulun Zhang, Matthew Fontaine, Varun Bhatt, Stefanos Nikolaidis, Jiaoyang Li

We study the problem of generating arbitrarily large environments to improve the throughput of multi-robot systems. Prior work proposes Quality Diversity (QD) algorithms as an effective method for optimizing the environments of automated warehouses. However, these approaches optimize only relatively small environments, falling short when it comes to replicating real-world warehouse sizes. The challenge arises from the exponential increase in the search space as the environment size increases. Additionally, the previous methods have only been tested with up to 350 robots in simulations, while practical warehouses could host thousands of robots. In this paper, instead of optimizing environments, we propose to optimize Neural Cellular Automata (NCA) environment generators via QD algorithms. We train a collection of NCA generators with QD algorithms in small environments and then generate arbitrarily large environments from the generators at test time. We show that NCA environment generators maintain consistent, regularized patterns regardless of environment size, significantly enhancing the scalability of multi-robot systems in two different domains with up to 2,350 robots. Additionally, we demonstrate that our method scales a single-agent reinforcement learning policy to arbitrarily large environments with similar patterns. We include the source code at https://github.com/lunjohnzhang/warehouse_env_gen_nca_public.

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/

Deep Learning/Recurrent Networks

Guan Wang, Yuhao Sun, Sijie Cheng, Sen Song

Recurrent spiking neural networks (RSNNs) hold great potential for advancing artificial general intelligence, as they draw inspiration from the biological nervous system and show promise in modeling complex dynamics.However, the widely-used surrogate gradient-based training methods for RSNNs are inherently inaccurate and unfriendly to neuromorphic hardware.To address these limitations, we propose the evolving connectivity (EC) framework, an inference-only method for training RSNNs.The EC framework reformulates weight-tuning as a search into parameterized connection probability distributions, and employs Natural Evolution Strategies (NES) for optimizing these distributions.Our EC framework circumvents the need for gradients and features hardware-friendly characteristics, including sparse boolean connections and high scalability.We evaluate EC on a series of standard robotic locomotion tasks, where it achieves comparable performance with deep neural networks and outperforms gradient-trained RSNNs, even solving the complex 17-DoF humanoid task.Additionally, the EC framework demonstrates a two to three fold speedup in efficiency compared to directly evolving parameters.By providing a performant and hardware-friendly alternative, the EC framework lays the groundwork for further energy-efficient applications of RSNNs and advances the development of neuromorphic devices.Our code is publicly available at https://github.com/imoneoi/EvolvingConnectivity.

Applications/Robotics

Xiaohan Wang, Yuehu Liu, Xinhang Song, Beibei Wang, Shuqiang Jiang

Visual navigation has been widely studied under the assumption that there may be several clear routes to reach the goal. However, in more practical scenarios such as a house with several messy rooms, there may not. Interactive Navigation (InterNav) considers agents navigating to their goals more effectively with object interactions, posing new challenges of learning interaction dynamics and extra action space. Previous works learn single vision-to-action policy with the guidance of designed representations. However, the causality between actions and outcomes is prone to be confounded when the attributes of obstacles are diverse and hard to measure. Learning policy for long-term action planning in complex scenes also leads to extensive inefficient exploration. In this paper, we introduce a causal diagram of InterNav clarifying the confounding bias caused by obstacles. To address the problem, we propose a multi-policy model that enables the exploration of counterfactual interactions as well as reduces unnecessary exploration. We develop a large-scale dataset containing 600k task episodes in 12k multi-room scenes based on the ProcTHOR simulator and showcase the effectiveness of our method with the evaluations on our dataset.

Reinforcement Learning/Batch Offline

Jiayi Guan, Guang Chen, Jiaming Ji, Long Yang, ao zhou, Zhijun Li, changjun jiang

Offline safe reinforcement learning (RL) algorithms promise to learn policies that satisfy safety constraints directly in offline datasets without interacting with the environment. This arrangement is particularly important in scenarios with high sampling costs and potential dangers, such as autonomous driving and robotics. However, the influence of safety constraints and out-of-distribution (OOD) actions have made it challenging for previous methods to achieve high reward returns while ensuring safety. In this work, we propose a Variational Optimization with Conservative Eestimation algorithm (VOCE) to solve the problem of optimizing safety policies in the offline dataset. Concretely, we reframe the problem of offline safe RL using probabilistic inference, which introduces variational distributions to make the optimization of policies more flexible. Subsequently, we utilize pessimistic estimation methods to estimate the Q-value of cost and reward, which mitigates the extrapolation errors induced by OOD actions. Finally, extensive experiments demonstrate that the VOCE algorithm achieves competitive performance across multiple experimental tasks, particularly outperforming state-of-the-art algorithms in terms of safety.

Deep Learning/Generative Models and Autoencoders

Hao Liu, Wilson Yan, Pieter Abbeel

Recent progress in scaling up large language models has shown impressive capabilities in performing few-shot learning across a wide range of natural language tasks. However, a key limitation is that these language models fundamentally lack grounding to visual perception - a crucial attribute needed to extend to real world tasks such as in visual-question answering and robotics. While prior works have largely connected image to text through pretraining or fine-tuning, learning such alignments are generally costly due to a combination of curating massive datasets and large computational burdens. In order to resolve these limitations, we propose a simple yet effective approach called Language-Quantized AutoEncoder (LQAE), a modification of VQ-VAE that learns to align text-image data in an unsupervised manner by leveraging pretrained language model denoisers (e.g., BERT). Our main idea is to encode images as sequences of text tokens by directly quantizing image embeddings using a pretrained language codebook. We then feed a masked version of the quantized embeddings into a BERT to reconstruct the original input. By doing so, LQAE learns to represent similar images with similar clusters of text tokens, thereby aligning these two modalities without the use of aligned text-image pairs. We show LQAE learns text-aligned image tokens that enable few-shot multi-modal learning with large language models, outperforming baseline methods in tasks such as image classification and VQA while requiring as few as 1-10 image-text pairs.

Applications/Robotics

Moran Barenboim, Vadim Indelman

Autonomous agents operating in real-world scenarios frequently encounter uncertainty and make decisions based on incomplete information. Planning under uncertainty can be mathematically formalized using partially observable Markov decision processes (POMDPs). However, finding an optimal plan for POMDPs can be computationally expensive and is feasible only for small tasks. In recent years, approximate algorithms, such as tree search and sample-based methodologies, have emerged as state-of-the-art POMDP solvers for larger problems. Despite their effectiveness, these algorithms offer only probabilistic and often asymptotic guarantees toward the optimal solution due to their dependence on sampling. To address these limitations, we derive a deterministic relationship between a simplified solution that iseasier to obtain and the theoretically optimal one. First, we derive bounds for selecting a subset of the observations to branch from while computing a complete belief at each posterior node. Then, since a complete belief update may be computationally demanding, we extend the bounds to support reduction of both the state and the observation spaces. We demonstrate how our guarantees can be integrated with existing state-of-the-art solvers that sample a subset of states and observations. As a result, the returned solution holds deterministic bounds relative to the optimal policy. Lastly, we substantiate our findings with supporting experimental results.

Reinforcement Learning/Deep RL

Zizhao Wang, Jiaheng Hu, Peter Stone, Roberto Martín-Martín

Tasks with large state space and sparse rewards present a longstanding challenge to reinforcement learning. In these tasks, an agent needs to explore the state space efficiently until it finds a reward. To deal with this problem, the community has proposed to augment the reward function with intrinsic reward, a bonus signal that encourages the agent to visit interesting states. In this work, we propose a new way of defining interesting states for environments with factored state spaces and complex chained dependencies, where an agent's actions may change the value of one entity that, in order, may affect the value of another entity. Our insight is that, in these environments, interesting states for exploration are states where the agent is uncertain whether (as opposed to how) entities such as the agent or objects have some influence on each other. We present ELDEN, Exploration via Local DepENdencies, a novel intrinsic reward that encourages the discovery of new interactions between entities. ELDEN utilizes a novel scheme --- the partial derivative of the learned dynamics to model the local dependencies between entities accurately and computationally efficiently. The uncertainty of the predicted dependencies is then used as an intrinsic reward to encourage exploration toward new interactions. We evaluate the performance of ELDEN on four different domains with complex dependencies, ranging from 2D grid worlds to 3D robotic tasks. In all domains, ELDEN correctly identifies local dependencies and learns successful policies, significantly outperforming previous state-of-the-art exploration methods.

Reinforcement Learning

Akhil Bagaria, Ben Abbatematteo, Omer Gottesman, Matt Corsaro, Sreehari Rammohan, George Konidaris

An agent learning an option in hierarchical reinforcement learning must solve three problems: identify the option's subgoal (termination condition), learn a policy, and learn where that policy will succeed (initiation set). The termination condition is typically identified first, but the option policy and initiation set must be learned simultaneously, which is challenging because the initiation set depends on the option policy, which changes as the agent learns. Consequently, data obtained from option execution becomes invalid over time, leading to an inaccurate initiation set that subsequently harms downstream task performance. We highlight three issues---data non-stationarity, temporal credit assignment, and pessimism---specific to learning initiation sets, and propose to address them using tools from off-policy value estimation and classification. We show that our method learns higher-quality initiation sets faster than existing methods (in MiniGrid and Montezuma's Revenge), can automatically discover promising grasps for robot manipulation (in Robosuite), and improves the performance of a state-of-the-art option discovery method in a challenging maze navigation task in MuJoCo.