Searcharxiv⌕ Search

arXiv subjects

Pulkit Agrawal

Publications and source records attributed to Pulkit Agrawal.

At least 91 records · Page 5Linked to original sources
arXiv2023

Is Conditional Generative Modeling all you need for Decision-Making?

Recent improvements in conditional generative modeling have made it possible to generate high-quality images from language descriptions alone. We investigate whether these methods can directly address the problem of sequential decision-making. We view decision-making not through the lens of reinforcement learning (RL), but rather through conditional generative modeling. To our surprise, we find that our formulation leads to policies that can outperform existing offline RL approaches across standard benchmarks. By modeling a policy as a return-conditional diffusion model, we illustrate how we may circumvent the need for dynamic programming and subsequently eliminate many of the complexities that come with traditional offline RL. We further demonstrate the advantages of modeling policies as conditional diffusion models by considering two other conditioning variables: constraints and skills. Conditioning on a single constraint or skill during training leads to behaviors at test-time that can satisfy several constraints together or demonstrate a composition of skills. Our results illustrate that conditional generative modeling is a powerful tool for decision-making.

cs.LG↗
arXiv2023

Shelving, Stacking, Hanging: Relational Pose Diffusion for Multi-modal Rearrangement

We propose a system for rearranging objects in a scene to achieve a desired object-scene placing relationship, such as a book inserted in an open slot of a bookshelf. The pipeline generalizes to novel geometries, poses, and layouts of both scenes and objects, and is trained from demonstrations to operate directly on 3D point clouds. Our system overcomes challenges associated with the existence of many geometrically-similar rearrangement solutions for a given scene. By leveraging an iterative pose de-noising training procedure, we can fit multi-modal demonstration data and produce multi-modal outputs while remaining precise and accurate. We also show the advantages of conditioning on relevant local geometric features while ignoring irrelevant global structure that harms both generalization and precision. We demonstrate our approach on three distinct rearrangement tasks that require handling multi-modality and generalization over object shape and pose in both simulation and the real world. Project website, code, and videos: https://anthonysimeonov.github.io/rpdiff-multi-modal/

cs.RO↗
arXiv2023

Topological Experience Replay

State-of-the-art deep Q-learning methods update Q-values using state transition tuples sampled from the experience replay buffer. This strategy often uniformly and randomly samples or prioritizes data sampling based on measures such as the temporal difference (TD) error. Such sampling strategies can be inefficient at learning Q-function because a state's Q-value depends on the Q-value of successor states. If the data sampling strategy ignores the precision of the Q-value estimate of the next state, it can lead to useless and often incorrect updates to the Q-values. To mitigate this issue, we organize the agent's experience into a graph that explicitly tracks the dependency between Q-values of states. Each edge in the graph represents a transition between two states by executing a single action. We perform value backups via a breadth-first search starting from that expands vertices in the graph starting from the set of terminal states and successively moving backward. We empirically show that our method is substantially more data-efficient than several baselines on a diverse range of goal-reaching tasks. Notably, the proposed method also outperforms baselines that consume more batches of training experience and operates from high-dimensional observational data such as images.

cs.LG↗
arXiv2023

Bilinear value networks

The dominant framework for off-policy multi-goal reinforcement learning involves estimating goal conditioned Q-value function. When learning to achieve multiple goals, data efficiency is intimately connected with the generalization of the Q-function to new goals. The de-facto paradigm is to approximate Q(s, a, g) using monolithic neural networks. To improve the generalization of the Q-function, we propose a bilinear decomposition that represents the Q-value via a low-rank approximation in the form of a dot product between two vector fields. The first vector field, f(s, a), captures the environment's local dynamics at the state s; whereas the second component, ϕ(s, g), captures the global relationship between the current state and the goal. We show that our bilinear decomposition scheme substantially improves data efficiency, and has superior transfer to out-of-distribution goals compared to prior methods. Empirical evidence is provided on the simulated Fetch robot task-suite and dexterous manipulation with a Shadow hand.

cs.AI↗
arXiv2023

Harnessing Mixed Offline Reinforcement Learning Datasets via Trajectory Weighting

Most offline reinforcement learning (RL) algorithms return a target policy maximizing a trade-off between (1) the expected performance gain over the behavior policy that collected the dataset, and (2) the risk stemming from the out-of-distribution-ness of the induced state-action occupancy. It follows that the performance of the target policy is strongly related to the performance of the behavior policy and, thus, the trajectory return distribution of the dataset. We show that in mixed datasets consisting of mostly low-return trajectories and minor high-return trajectories, state-of-the-art offline RL algorithms are overly restrained by low-return trajectories and fail to exploit high-performing trajectories to the fullest. To overcome this issue, we show that, in deterministic MDPs with stochastic initial states, the dataset sampling can be re-weighted to induce an artificial dataset whose behavior policy has a higher return. This re-weighted sampling strategy may be combined with any offline RL algorithm. We further analyze that the opportunity for performance improvement over the behavior policy correlates with the positive-sided variance of the returns of the trajectories in the dataset. We empirically show that while CQL, IQL, and TD3+BC achieve only a part of this potential policy improvement, these same algorithms combined with our reweighted sampling strategy fully exploit the dataset. Furthermore, we empirically demonstrate that, despite its theoretical limitation, the approach may still be efficient in stochastic environments. The code is available at https://github.com/Improbable-AI/harness-offline-rl.

cs.LG↗
arXiv2023

Self-Supervised Reinforcement Learning that Transfers using Random Features

Model-free reinforcement learning algorithms have exhibited great potential in solving single-task sequential decision-making problems with high-dimensional observations and long horizons, but are known to be hard to generalize across tasks. Model-based RL, on the other hand, learns task-agnostic models of the world that naturally enables transfer across different reward functions, but struggles to scale to complex environments due to the compounding error. To get the best of both worlds, we propose a self-supervised reinforcement learning method that enables the transfer of behaviors across tasks with different rewards, while circumventing the challenges of model-based RL. In particular, we show self-supervised pre-training of model-free reinforcement learning with a number of random features as rewards allows implicit modeling of long-horizon environment dynamics. Then, planning techniques like model-predictive control using these implicit models enable fast adaptation to problems with new reward functions. Our method is self-supervised in that it can be trained on offline datasets without reward labels, but can then be quickly deployed on new tasks. We validate that our proposed method enables transfer across tasks on a variety of manipulation and locomotion domains in simulation, opening the door to generalist decision-making agents.

cs.LG↗
arXiv2023

Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks

This work examines the challenges of training neural networks using vector quantization using straight-through estimation. We find that a primary cause of training instability is the discrepancy between the model embedding and the code-vector distribution. We identify the factors that contribute to this issue, including the codebook gradient sparsity and the asymmetric nature of the commitment loss, which leads to misaligned code-vector assignments. We propose to address this issue via affine re-parameterization of the code vectors. Additionally, we introduce an alternating optimization to reduce the gradient error introduced by the straight-through estimation. Moreover, we propose an improvement to the commitment loss to ensure better alignment between the codebook representation and the model embedding. These optimization methods improve the mathematical approximation of the straight-through estimation and, ultimately, the model performance. We demonstrate the effectiveness of our methods on several common model architectures, such as AlexNet, ResNet, and ViT, across various tasks, including image classification and generative modeling.

cs.LG↗
arXiv2023

Learning to Extrapolate: A Transductive Approach

Machine learning systems, especially with overparameterized deep neural networks, can generalize to novel test instances drawn from the same distribution as the training data. However, they fare poorly when evaluated on out-of-support test points. In this work, we tackle the problem of developing machine learning systems that retain the power of overparameterized function approximators while enabling extrapolation to out-of-support test points when possible. This is accomplished by noting that under certain conditions, a "transductive" reparameterization can convert an out-of-support extrapolation problem into a problem of within-support combinatorial generalization. We propose a simple strategy based on bilinear embeddings to enable this type of combinatorial generalization, thereby addressing the out-of-support extrapolation problem under certain conditions. We instantiate a simple, practical algorithm applicable to various supervised learning and imitation learning tasks.

cs.LG↗
arXiv2023

Constructive Assimilation: Boosting Contrastive Learning Performance through View Generation Strategies

Transformations based on domain expertise (expert transformations), such as random-resized-crop and color-jitter, have proven critical to the success of contrastive learning techniques such as SimCLR. Recently, several attempts have been made to replace such domain-specific, human-designed transformations with generated views that are learned. However for imagery data, so far none of these view-generation methods has been able to outperform expert transformations. In this work, we tackle a different question: instead of replacing expert transformations with generated views, can we constructively assimilate generated views with expert transformations? We answer this question in the affirmative and propose a view generation method and a simple, effective assimilation method that together improve the state-of-the-art by up to ~3.6% on three different datasets. Importantly, we conduct a detailed empirical study that systematically analyzes a range of view generation and assimilation methods and provides a holistic picture of the efficacy of learned views in contrastive representation learning.

cs.CV↗
arXiv2023

DribbleBot: Dynamic Legged Manipulation in the Wild

DribbleBot (Dexterous Ball Manipulation with a Legged Robot) is a legged robotic system that can dribble a soccer ball under the same real-world conditions as humans (i.e., in-the-wild). We adopt the paradigm of training policies in simulation using reinforcement learning and transferring them into the real world. We overcome critical challenges of accounting for variable ball motion dynamics on different terrains and perceiving the ball using body-mounted cameras under the constraints of onboard computing. Our results provide evidence that current quadruped platforms are well-suited for studying dynamic whole-body control problems involving simultaneous locomotion and manipulation directly from sensory observations.

cs.RO↗
arXiv2023

The Low-Rank Simplicity Bias in Deep Networks

Modern deep neural networks are highly over-parameterized compared to the data on which they are trained, yet they often generalize remarkably well. A flurry of recent work has asked: why do deep networks not overfit to their training data? In this work, we make a series of empirical observations that investigate and extend the hypothesis that deeper networks are inductively biased to find solutions with lower effective rank embeddings. We conjecture that this bias exists because the volume of functions that maps to low effective rank embedding increases with depth. We show empirically that our claim holds true on finite width linear and non-linear models on practical learning paradigms and show that on natural data, these are often the solutions that generalize well. We then show that the simplicity bias exists at both initialization and after training and is resilient to hyper-parameters and learning methods. We further demonstrate how linear over-parameterization of deep non-linear models can be used to induce low-rank bias, improving generalization performance on CIFAR and ImageNet without changing the modeling capacity.

cs.LG↗
arXiv2023

TactoFind: A Tactile Only System for Object Retrieval

We study the problem of object retrieval in scenarios where visual sensing is absent, object shapes are unknown beforehand and objects can move freely, like grabbing objects out of a drawer. Successful solutions require localizing free objects, identifying specific object instances, and then grasping the identified objects, only using touch feedback. Unlike vision, where cameras can observe the entire scene, touch sensors are local and only observe parts of the scene that are in contact with the manipulator. Moreover, information gathering via touch sensors necessitates applying forces on the touched surface which may disturb the scene itself. Reasoning with touch, therefore, requires careful exploration and integration of information over time -- a challenge we tackle. We present a system capable of using sparse tactile feedback from fingertip touch sensors on a dexterous hand to localize, identify and grasp novel objects without any visual feedback. Videos are available at https://taochenshh.github.io/projects/tactofind.

cs.RO↗
arXiv2023

Geometry of contact: contact planning for multi-legged robots via spin models duality

Contact planning is crucial in locomoting systems.Specifically, appropriate contact planning can enable versatile behaviors (e.g., sidewinding in limbless locomotors) and facilitate speed-dependent gait transitions (e.g., walk-trot-gallop in quadrupedal locomotors). The challenges of contact planning include determining not only the sequence by which contact is made and broken between the locomotor and the environments, but also the sequence of internal shape changes (e.g., body bending and limb shoulder joint oscillation). Most state-of-art contact planning algorithms focused on conventional robots (e.g.biped and quadruped) and conventional tasks (e.g. forward locomotion), and there is a lack of study on general contact planning in multi-legged robots. In this paper, we show that using geometric mechanics framework, we can obtain the global optimal contact sequence given the internal shape changes sequence. Therefore, we simplify the contact planning problem to a graph optimization problem to identify the internal shape changes. Taking advantages of the spatio-temporal symmetry in locomotion, we map the graph optimization problem to special cases of spin models, which allows us to obtain the global optima in polynomial time. We apply our approach to develop new forward and sidewinding behaviors in a hexapod and a 12-legged centipede. We verify our predictions using numerical and robophysical models, and obtain novel and effective locomotion behaviors.

cs.RO↗
arXiv2022

Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behavior

Learned locomotion policies can rapidly adapt to diverse environments similar to those experienced during training but lack a mechanism for fast tuning when they fail in an out-of-distribution test environment. This necessitates a slow and iterative cycle of reward and environment redesign to achieve good performance on a new task. As an alternative, we propose learning a single policy that encodes a structured family of locomotion strategies that solve training tasks in different ways, resulting in Multiplicity of Behavior (MoB). Different strategies generalize differently and can be chosen in real-time for new tasks or environments, bypassing the need for time-consuming retraining. We release a fast, robust open-source MoB locomotion controller, Walk These Ways, that can execute diverse gaits with variable footswing, posture, and speed, unlocking diverse downstream tasks: crouching, hopping, high-speed running, stair traversal, bracing against shoves, rhythmic dance, and more. Video and code release: https://gmargo11.github.io/walk-these-ways/

cs.RO↗
arXiv2022

Discovering Generalizable Spatial Goal Representations via Graph-based Active Reward Learning

In this work, we consider one-shot imitation learning for object rearrangement tasks, where an AI agent needs to watch a single expert demonstration and learn to perform the same task in different environments. To achieve a strong generalization, the AI agent must infer the spatial goal specification for the task. However, there can be multiple goal specifications that fit the given demonstration. To address this, we propose a reward learning approach, Graph-based Equivalence Mappings (GEM), that can discover spatial goal representations that are aligned with the intended goal specification, enabling successful generalization in unseen environments. Specifically, GEM represents a spatial goal specification by a reward function conditioned on i) a graph indicating important spatial relationships between objects and ii) state equivalence mappings for each edge in the graph indicating invariant properties of the corresponding relationship. GEM combines inverse reinforcement learning and active reward learning to efficiently improve the reward function by utilizing the graph structure and domain randomization enabled by the equivalence mappings. We conducted experiments with simulated oracles and with human subjects. The results show that GEM can drastically improve the generalizability of the learned goal representations over strong baselines.

cs.LG↗
arXiv2022

Redeeming Intrinsic Rewards via Constrained Optimization

State-of-the-art reinforcement learning (RL) algorithms typically use random sampling (e.g., $ε$-greedy) for exploration, but this method fails on hard exploration tasks like Montezuma's Revenge. To address the challenge of exploration, prior works incentivize exploration by rewarding the agent when it visits novel states. Such intrinsic rewards (also called exploration bonus or curiosity) often lead to excellent performance on hard exploration tasks. However, on easy exploration tasks, the agent gets distracted by intrinsic rewards and performs unnecessary exploration even when sufficient task (also called extrinsic) reward is available. Consequently, such an overly curious agent performs worse than an agent trained with only task reward. Such inconsistency in performance across tasks prevents the widespread use of intrinsic rewards with RL algorithms. We propose a principled constrained optimization procedure called Extrinsic-Intrinsic Policy Optimization (EIPO) that automatically tunes the importance of the intrinsic reward: it suppresses the intrinsic reward when exploration is unnecessary and increases it when exploration is required. The results is superior exploration that does not require manual tuning in balancing the intrinsic reward against the task reward. Consistent performance gains across sixty-one ATARI games validate our claim. The code is available at https://github.com/Improbable-AI/eipo.

cs.LG↗
arXiv2022

SE(3)-Equivariant Relational Rearrangement with Neural Descriptor Fields

We present a method for performing tasks involving spatial relations between novel object instances initialized in arbitrary poses directly from point cloud observations. Our framework provides a scalable way for specifying new tasks using only 5-10 demonstrations. Object rearrangement is formalized as the question of finding actions that configure task-relevant parts of the object in a desired alignment. This formalism is implemented in three steps: assigning a consistent local coordinate frame to the task-relevant object parts, determining the location and orientation of this coordinate frame on unseen object instances, and executing an action that brings these frames into the desired alignment. We overcome the key technical challenge of determining task-relevant local coordinate frames from a few demonstrations by developing an optimization method based on Neural Descriptor Fields (NDFs) and a single annotated 3D keypoint. An energy-based learning scheme to model the joint configuration of the objects that satisfies a desired relational task further improves performance. The method is tested on three multi-object rearrangement tasks in simulation and on a real robot. Project website, videos, and code: https://anthonysimeonov.github.io/r-ndf/

cs.RO↗
arXiv2022

Stable Object Reorientation using Contact Plane Registration

We present a system for accurately predicting stable orientations for diverse rigid objects. We propose to overcome the critical issue of modelling multimodality in the space of rotations by using a conditional generative model to accurately classify contact surfaces. Our system is capable of operating from noisy and partially-observed pointcloud observations captured by real world depth cameras. Our method substantially outperforms the current state-of-the-art systems on a simulated stacking task requiring highly accurate rotations, and demonstrates strong sim2real zero-shot transfer results across a variety of unseen objects on a real world reorientation task. Project website: \url{https://richardrl.github.io/stable-reorientation/}

cs.RO↗