arXiv subjects

Pulkit Agrawal

Publications and source records attributed to Pulkit Agrawal.

At least 109 records · Page 6Linked to original sources

arXiv2022

Offline RL Policies Should be Trained to be Adaptive

Offline RL algorithms must account for the fact that the dataset they are provided may leave many facets of the environment unknown. The most common way to approach this challenge is to employ pessimistic or conservative methods, which avoid behaviors that are too dissimilar from those in the training dataset. However, relying exclusively on conservatism has drawbacks: performance is sensitive to the exact degree of conservatism, and conservative objectives can recover highly suboptimal policies. In this work, we propose that offline RL methods should instead be adaptive in the presence of uncertainty. We show that acting optimally in offline RL in a Bayesian sense involves solving an implicit POMDP. As a result, optimal policies for offline RL must be adaptive, depending not just on the current state but rather all the transitions seen so far during evaluation.We present a model-free algorithm for approximating this optimal adaptive policy, and demonstrate the efficacy of learning such adaptive policies in offline RL benchmarks.

cs.LG↗

arXiv2022

Overcoming the Spectral Bias of Neural Value Approximation

Value approximation using deep neural networks is at the heart of off-policy deep reinforcement learning, and is often the primary module that provides learning signals to the rest of the algorithm. While multi-layer perceptron networks are universal function approximators, recent works in neural kernel regression suggest the presence of a spectral bias, where fitting high-frequency components of the value function requires exponentially more gradient update steps than the low-frequency ones. In this work, we re-examine off-policy reinforcement learning through the lens of kernel regression and propose to overcome such bias via a composite neural tangent kernel. With just a single line-change, our approach, the Fourier feature networks (FFN) produce state-of-the-art performance on challenging continuous control domains with only a fraction of the compute. Faster convergence and better off-policy stability also make it possible to remove the target network without suffering catastrophic divergences, which further reduces TD}(0)'s estimation bias on a few tasks.

cs.LG↗

arXiv2022

Rapid Locomotion via Reinforcement Learning

Agile maneuvers such as sprinting and high-speed turning in the wild are challenging for legged robots. We present an end-to-end learned controller that achieves record agility for the MIT Mini Cheetah, sustaining speeds up to 3.9 m/s. This system runs and turns fast on natural terrains like grass, ice, and gravel and responds robustly to disturbances. Our controller is a neural network trained in simulation via reinforcement learning and transferred to the real world. The two key components are (i) an adaptive curriculum on velocity commands and (ii) an online system identification strategy for sim-to-real transfer leveraged from prior work. Videos of the robot's behaviors are available at: https://agility.csail.mit.edu/

cs.RO↗

arXiv2022

An Integrated Design Pipeline for Tactile Sensing Robotic Manipulators

Traditional robotic manipulator design methods require extensive, time-consuming, and manual trial and error to produce a viable design. During this process, engineers often spend their time redesigning or reshaping components as they discover better topologies for the robotic manipulator. Tactile sensors, while useful, often complicate the design due to their bulky form factor. We propose an integrated design pipeline to streamline the design and manufacturing of robotic manipulators with knitted, glove-like tactile sensors. The proposed pipeline allows a designer to assemble a collection of modular, open-source components by applying predefined graph grammar rules. The end result is an intuitive design paradigm that allows the creation of new virtual designs of manipulators in a matter of minutes. Our framework allows the designer to fine-tune the manipulator's shape through cage-based geometry deformation. Finally, the designer can select surfaces for adding tactile sensing. Once the manipulator design is finished, the program will automatically generate 3D printing and knitting files for manufacturing. We demonstrate the utility of this pipeline by creating four custom manipulators tested on real-world tasks: screwing in a wing screw, sorting water bottles, picking up an egg, and cutting paper with scissors.

cs.RO↗

arXiv2022

Equivariant Contrastive Learning

In state-of-the-art self-supervised learning (SSL) pre-training produces semantically good representations by encouraging them to be invariant under meaningful transformations prescribed from human knowledge. In fact, the property of invariance is a trivial instance of a broader class called equivariance, which can be intuitively understood as the property that representations transform according to the way the inputs transform. Here, we show that rather than using only invariance, pre-training that encourages non-trivial equivariance to some transformations, while maintaining invariance to other transformations, can be used to improve the semantic quality of representations. Specifically, we extend popular SSL methods to a more general framework which we name Equivariant Self-Supervised Learning (E-SSL). In E-SSL, a simple additional pre-training objective encourages equivariance by predicting the transformations applied to the input. We demonstrate E-SSL's effectiveness empirically on several popular computer vision benchmarks, e.g. improving SimCLR to 72.5% linear probe accuracy on ImageNet. Furthermore, we demonstrate usefulness of E-SSL for applications beyond computer vision; in particular, we show its utility on regression problems in photonics science. Our code, datasets and pre-trained models are available at https://github.com/rdangovs/essl to aid further research in E-SSL.

cs.CV↗

arXiv2022

Stubborn: A Strong Baseline for Indoor Object Navigation

We present a strong baseline that surpasses the performance of previously published methods on the Habitat Challenge task of navigating to a target object in indoor environments. Our method is motivated from primary failure modes of prior state-of-the-art: poor exploration, inaccurate object identification, and agent getting trapped due to imprecise map construction. We make three contributions to mitigate these issues: (i) First, we show that existing map-based methods fail to effectively use semantic clues for exploration. We present a semantic-agnostic exploration strategy (called Stubborn) without any learning that surprisingly outperforms prior work. (ii) We propose a strategy for integrating temporal information to improve object identification. (iii) Lastly, due to inaccurate depth observation the agent often gets trapped in small regions. We develop a multi-scale collision map for obstacle identification that mitigates this issue.

cs.RO↗

arXiv2021

Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation

We present Neural Descriptor Fields (NDFs), an object representation that encodes both points and relative poses between an object and a target (such as a robot gripper or a rack used for hanging) via category-level descriptors. We employ this representation for object manipulation, where given a task demonstration, we want to repeat the same task on a new object instance from the same category. We propose to achieve this objective by searching (via optimization) for the pose whose descriptor matches that observed in the demonstration. NDFs are conveniently trained in a self-supervised fashion via a 3D auto-encoding task that does not rely on expert-labeled keypoints. Further, NDFs are SE(3)-equivariant, guaranteeing performance that generalizes across all possible 3D object translations and rotations. We demonstrate learning of manipulation tasks from few (5-10) demonstrations both in simulation and on a real robot. Our performance generalizes across both object instances and 6-DoF object poses, and significantly outperforms a recent baseline that relies on 2D descriptors. Project website: https://yilundu.github.io/ndf/.

cs.RO↗

arXiv2021

3D Neural Scene Representations for Visuomotor Control

Humans have a strong intuitive understanding of the 3D environment around us. The mental model of the physics in our brain applies to objects of different materials and enables us to perform a wide range of manipulation tasks that are far beyond the reach of current robots. In this work, we desire to learn models for dynamic 3D scenes purely from 2D visual observations. Our model combines Neural Radiance Fields (NeRF) and time contrastive learning with an autoencoding framework, which learns viewpoint-invariant 3D-aware scene representations. We show that a dynamics model, constructed over the learned representation space, enables visuomotor control for challenging manipulation tasks involving both rigid bodies and fluids, where the target is specified in a viewpoint different from what the robot operates on. When coupled with an auto-decoding framework, it can even support goal specification from camera viewpoints that are outside the training distribution. We further demonstrate the richness of the learned 3D dynamics model by performing future prediction and novel view synthesis. Finally, we provide detailed ablation studies regarding different system designs and qualitative analysis of the learned representations.

cs.RO↗

arXiv2021

A System for General In-Hand Object Re-Orientation

In-hand object reorientation has been a challenging problem in robotics due to high dimensional actuation space and the frequent change in contact state between the fingers and the objects. We present a simple model-free framework that can learn to reorient objects with both the hand facing upwards and downwards. We demonstrate the capability of reorienting over 2000 geometrically different objects in both cases. The learned policies show strong zero-shot transfer performance on new objects. We provide evidence that these policies are amenable to real-world operation by distilling them to use observations easily available in the real world. The videos of the learned policies are available at: https://taochenshh.github.io/projects/in-hand-reorientation.

cs.RO↗

arXiv2021

Learning to Jump from Pixels

Today's robotic quadruped systems can robustly walk over a diverse range of rough but continuous terrains, where the terrain elevation varies gradually. Locomotion on discontinuous terrains, such as those with gaps or obstacles, presents a complementary set of challenges. In discontinuous settings, it becomes necessary to plan ahead using visual inputs and to execute agile behaviors beyond robust walking, such as jumps. Such dynamic motion results in significant motion of onboard sensors, which introduces a new set of challenges for real-time visual processing. The requirement for agility and terrain awareness in this setting reinforces the need for robust control. We present Depth-based Impulse Control (DIC), a method for synthesizing highly agile visually-guided locomotion behaviors. DIC affords the flexibility of model-free learning but regularizes behavior through explicit model-based optimization of ground reaction forces. We evaluate the proposed method both in simulation and in the real world.

cs.RO↗

arXiv2021

Residual Model Learning for Microrobot Control

A majority of microrobots are constructed using compliant materials that are difficult to model analytically, limiting the utility of traditional model-based controllers. Challenges in data collection on microrobots and large errors between simulated models and real robots make current model-based learning and sim-to-real transfer methods difficult to apply. We propose a novel framework residual model learning (RML) that leverages approximate models to substantially reduce the sample complexity associated with learning an accurate robot model. We show that using RML, we can learn a model of the Harvard Ambulatory MicroRobot (HAMR) using just 12 seconds of passively collected interaction data. The learned model is accurate enough to be leveraged as "proxy-simulator" for learning walking and turning behaviors using model-free reinforcement learning algorithms. RML provides a general framework for learning from extremely small amounts of interaction data, and our experiments with HAMR clearly demonstrate that RML substantially outperforms existing techniques.

cs.RO↗

arXiv2021

An End-to-End Differentiable Framework for Contact-Aware Robot Design

The current dominant paradigm for robotic manipulation involves two separate stages: manipulator design and control. Because the robot's morphology and how it can be controlled are intimately linked, joint optimization of design and control can significantly improve performance. Existing methods for co-optimization are limited and fail to explore a rich space of designs. The primary reason is the trade-off between the complexity of designs that is necessary for contact-rich tasks against the practical constraints of manufacturing, optimization, contact handling, etc. We overcome several of these challenges by building an end-to-end differentiable framework for contact-aware robot design. The two key components of this framework are: a novel deformation-based parameterization that allows for the design of articulated rigid robots with arbitrary, complex geometry, and a differentiable rigid body simulator that can handle contact-rich scenarios and computes analytical gradients for a full spectrum of kinematic and dynamic parameters. On multiple manipulation tasks, our framework outperforms existing methods that either only optimize for control or for design using alternate representations or co-optimize using gradient-free methods.

cs.RO↗

arXiv2021

Learning Task Informed Abstractions

Current model-based reinforcement learning methods struggle when operating from complex visual scenes due to their inability to prioritize task-relevant features. To mitigate this problem, we propose learning Task Informed Abstractions (TIA) that explicitly separates reward-correlated visual features from distractors. For learning TIA, we introduce the formalism of Task Informed MDP (TiMDP) that is realized by training two models that learn visual features via cooperative reconstruction, but one model is adversarially dissociated from the reward signal. Empirical evaluation shows that TIA leads to significant performance gains over state-of-the-art methods on many visual control tasks where natural and unconstrained visual distractions pose a formidable challenge.

cs.LG↗

arXiv2021

OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning

Reinforcement learning (RL) has achieved impressive performance in a variety of online settings in which an agent's ability to query the environment for transitions and rewards is effectively unlimited. However, in many practical applications, the situation is reversed: an agent may have access to large amounts of undirected offline experience data, while access to the online environment is severely limited. In this work, we focus on this offline setting. Our main insight is that, when presented with offline data composed of a variety of behaviors, an effective way to leverage this data is to extract a continuous space of recurring and temporally extended primitive behaviors before using these primitives for downstream task learning. Primitives extracted in this way serve two purposes: they delineate the behaviors that are supported by the data from those that are not, making them useful for avoiding distributional shift in offline RL; and they provide a degree of temporal abstraction, which reduces the effective horizon yielding better learning in theory, and improved offline RL in practice. In addition to benefiting offline policy optimization, we show that performing offline primitive learning in this way can also be leveraged for improving few-shot imitation learning as well as exploration and transfer in online RL on a variety of benchmark domains. Visualizations are available at https://sites.google.com/view/opal-iclr

cs.LG↗

arXiv2020

A Long Horizon Planning Framework for Manipulating Rigid Pointcloud Objects

We present a framework for solving long-horizon planning problems involving manipulation of rigid objects that operates directly from a point-cloud observation, i.e. without prior object models. Our method plans in the space of object subgoals and frees the planner from reasoning about robot-object interaction dynamics by relying on a set of generalizable manipulation primitives. We show that for rigid bodies, this abstraction can be realized using low-level manipulation skills that maintain sticking contact with the object and represent subgoals as 3D transformations. To enable generalization to unseen objects and improve planning performance, we propose a novel way of representing subgoals for rigid-body manipulation and a graph-attention based neural network architecture for processing point-cloud inputs. We experimentally validate these choices using simulated and real-world experiments on the YuMi robot. Results demonstrate that our method can successfully manipulate new objects into target configurations requiring long-term planning. Overall, our framework realizes the best of the worlds of task-and-motion planning (TAMP) and learning-based approaches. Project website: https://anthonysimeonov.github.io/rpo-planning-framework/.

cs.RO↗

arXiv2020

AdaScale SGD: A User-Friendly Algorithm for Distributed Training

When using large-batch training to speed up stochastic gradient descent, learning rates must adapt to new batch sizes in order to maximize speed-ups and preserve model quality. Re-tuning learning rates is resource intensive, while fixed scaling rules often degrade model quality. We propose AdaScale SGD, an algorithm that reliably adapts learning rates to large-batch training. By continually adapting to the gradient's variance, AdaScale automatically achieves speed-ups for a wide range of batch sizes. We formally describe this quality with AdaScale's convergence bound, which maintains final objective values, even as batch sizes grow large and the number of iterations decreases. In empirical comparisons, AdaScale trains well beyond the batch size limits of popular "linear learning rate scaling" rules. This includes large-batch training with no model degradation for machine translation, image classification, object detection, and speech recognition tasks. AdaScale's qualitative behavior is similar to that of "warm-up" heuristics, but unlike warm-up, this behavior emerges naturally from a principled mechanism. The algorithm introduces negligible computational overhead and no new hyperparameters, making AdaScale an attractive choice for large-scale training in practice.

cs.LG↗

arXiv2020

Exploring Exploration: Comparing Children with RL Agents in Unified Environments

Research in developmental psychology consistently shows that children explore the world thoroughly and efficiently and that this exploration allows them to learn. In turn, this early learning supports more robust generalization and intelligent behavior later in life. While much work has gone into developing methods for exploration in machine learning, artificial agents have not yet reached the high standard set by their human counterparts. In this work we propose using DeepMind Lab (Beattie et al., 2016) as a platform to directly compare child and agent behaviors and to develop new exploration techniques. We outline two ongoing experiments to demonstrate the effectiveness of a direct comparison, and outline a number of open research questions that we believe can be tested using this methodology.

cs.AI↗

arXiv2019

Towards Practical Multi-Object Manipulation using Relational Reinforcement Learning

Learning robotic manipulation tasks using reinforcement learning with sparse rewards is currently impractical due to the outrageous data requirements. Many practical tasks require manipulation of multiple objects, and the complexity of such tasks increases with the number of objects. Learning from a curriculum of increasingly complex tasks appears to be a natural solution, but unfortunately, does not work for many scenarios. We hypothesize that the inability of the state-of-the-art algorithms to effectively utilize a task curriculum stems from the absence of inductive biases for transferring knowledge from simpler to complex tasks. We show that graph-based relational architectures overcome this limitation and enable learning of complex tasks when provided with a simple curriculum of tasks with increasing numbers of objects. We demonstrate the utility of our framework on a simulated block stacking task. Starting from scratch, our agent learns to stack six blocks into a tower. Despite using step-wise sparse rewards, our method is orders of magnitude more data-efficient and outperforms the existing state-of-the-art method that utilizes human demonstrations. Furthermore, the learned policy exhibits zero-shot generalization, successfully stacking blocks into taller towers and previously unseen configurations such as pyramids, without any further training.

cs.RO↗