Searcharxiv⌕ Search

arXiv subjects

Abhishek Gupta

Publications and source records attributed to Abhishek Gupta.

At least 109 records · Page 6Linked to original sources
arXiv2023

Fighting Uncertainty with Gradients: Offline Reinforcement Learning via Diffusion Score Matching

Gradient-based methods enable efficient search capabilities in high dimensions. However, in order to apply them effectively in offline optimization paradigms such as offline Reinforcement Learning (RL) or Imitation Learning (IL), we require a more careful consideration of how uncertainty estimation interplays with first-order methods that attempt to minimize them. We study smoothed distance to data as an uncertainty metric, and claim that it has two beneficial properties: (i) it allows gradient-based methods that attempt to minimize uncertainty to drive iterates to data as smoothing is annealed, and (ii) it facilitates analysis of model bias with Lipschitz constants. As distance to data can be expensive to compute online, we consider settings where we need amortize this computation. Instead of learning the distance however, we propose to learn its gradients directly as an oracle for first-order optimizers. We show these gradients can be efficiently learned with score-matching techniques by leveraging the equivalence between distance to data and data likelihood. Using this insight, we propose Score-Guided Planning (SGP), a planning algorithm for offline RL that utilizes score-matching to enable first-order planning in high-dimensional problems, where zeroth-order methods were unable to scale, and ensembles were unable to overcome local minima. Website: https://sites.google.com/view/score-guided-planning/home

cs.LG↗
arXiv2023

Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets

Offline policy learning is aimed at learning decision-making policies using existing datasets of trajectories without collecting additional data. The primary motivation for using reinforcement learning (RL) instead of supervised learning techniques such as behavior cloning is to find a policy that achieves a higher average return than the trajectories constituting the dataset. However, we empirically find that when a dataset is dominated by suboptimal trajectories, state-of-the-art offline RL algorithms do not substantially improve over the average return of trajectories in the dataset. We argue this is due to an assumption made by current offline RL algorithms of staying close to the trajectories in the dataset. If the dataset primarily consists of sub-optimal trajectories, this assumption forces the policy to mimic the suboptimal actions. We overcome this issue by proposing a sampling strategy that enables the policy to only be constrained to ``good data" rather than all actions in the dataset (i.e., uniform sampling). We present a realization of the sampling strategy and an algorithm that can be used as a plug-and-play module in standard offline RL algorithms. Our evaluation demonstrates significant performance gains in 72 imbalanced datasets, D4RL dataset, and across three different offline RL algorithms. Code is available at https://github.com/Improbable-AI/dw-offline-rl.

cs.LG↗
arXiv2023

Universal Visual Decomposer: Long-Horizon Manipulation Made Easy

Real-world robotic tasks stretch over extended horizons and encompass multiple stages. Learning long-horizon manipulation tasks, however, is a long-standing challenge, and demands decomposing the overarching task into several manageable subtasks to facilitate policy learning and generalization to unseen tasks. Prior task decomposition methods require task-specific knowledge, are computationally intensive, and cannot readily be applied to new tasks. To address these shortcomings, we propose Universal Visual Decomposer (UVD), an off-the-shelf task decomposition method for visual long horizon manipulation using pre-trained visual representations designed for robotic control. At a high level, UVD discovers subgoals by detecting phase shifts in the embedding space of the pre-trained representation. Operating purely on visual demonstrations without auxiliary information, UVD can effectively extract visual subgoals embedded in the videos, while incurring zero additional training cost on top of standard visuomotor policy training. Goal-conditioned policies learned with UVD-discovered subgoals exhibit significantly improved compositional generalization at test time to unseen tasks. Furthermore, UVD-discovered subgoals can be used to construct goal-based reward shaping that jump-starts temporally extended exploration for reinforcement learning. We extensively evaluate UVD on both simulation and real-world tasks, and in all cases, UVD substantially outperforms baselines across imitation and reinforcement learning settings on in-domain and out-of-domain task sequences alike, validating the clear advantage of automated visual task decomposition within the simple, compact UVD framework.

cs.RO↗
arXiv2023

RoboHive: A Unified Framework for Robot Learning

We present RoboHive, a comprehensive software platform and ecosystem for research in the field of Robot Learning and Embodied Artificial Intelligence. Our platform encompasses a diverse range of pre-existing and novel environments, including dexterous manipulation with the Shadow Hand, whole-arm manipulation tasks with Franka and Fetch robots, quadruped locomotion, among others. Included environments are organized within and cover multiple domains such as hand manipulation, locomotion, multi-task, multi-agent, muscles, etc. In comparison to prior works, RoboHive offers a streamlined and unified task interface taking dependency on only a minimal set of well-maintained packages, features tasks with high physics fidelity and rich visual diversity, and supports common hardware drivers for real-world deployment. The unified interface of RoboHive offers a convenient and accessible abstraction for algorithmic research in imitation, reinforcement, multi-task, and hierarchical learning. Furthermore, RoboHive includes expert demonstrations and baseline results for most environments, providing a standard for benchmarking and comparisons. Details: https://sites.google.com/view/robohive

cs.RO↗
arXiv2023

Maximizing Success Rate of Payment Routing using Non-stationary Bandits

This paper discusses the system architecture design and deployment of non-stationary multi-armed bandit approaches to determine a near-optimal payment routing policy based on the recent history of transactions. We propose a Routing Service architecture using a novel Ray-based implementation for optimally scaling bandit-based payment routing to over 10,000 transactions per second, adhering to the system design requirements and ecosystem constraints with Payment Card Industry Data Security Standard (PCI DSS). We first evaluate the effectiveness of multiple bandit-based payment routing algorithms on a custom simulator to benchmark multiple non-stationary bandit approaches and identify the best hyperparameters. We then conducted live experiments on the payment transaction system on a fantasy sports platform Dream11. In the live experiments, we demonstrated that our non-stationary bandit-based algorithm consistently improves the success rate of transactions by 0.92% compared to the traditional rule-based methods over one month.

cs.LG↗
arXiv2023

Hoeffding's Inequality for Markov Chains under Generalized Concentrability Condition

This paper studies Hoeffding's inequality for Markov chains under the generalized concentrability condition defined via integral probability metric (IPM). The generalized concentrability condition establishes a framework that interpolates and extends the existing hypotheses of Markov chain Hoeffding-type inequalities. The flexibility of our framework allows Hoeffding's inequality to be applied beyond the ergodic Markov chains in the traditional sense. We demonstrate the utility by applying our framework to several non-asymptotic analyses arising from the field of machine learning, including (i) a generalization bound for empirical risk minimization with Markovian samples, (ii) a finite sample guarantee for Ployak-Ruppert averaging of SGD, and (iii) a new regret bound for rested Markovian bandits with general state space.

stat.ML↗
arXiv2023

Open-Sourcing Highly Capable Foundation Models: An evaluation of risks, benefits, and alternative methods for pursuing open-source objectives

Recent decisions by leading AI labs to either open-source their models or to restrict access to their models has sparked debate about whether, and how, increasingly capable AI models should be shared. Open-sourcing in AI typically refers to making model architecture and weights freely and publicly accessible for anyone to modify, study, build on, and use. This offers advantages such as enabling external oversight, accelerating progress, and decentralizing control over AI development and use. However, it also presents a growing potential for misuse and unintended consequences. This paper offers an examination of the risks and benefits of open-sourcing highly capable foundation models. While open-sourcing has historically provided substantial net benefits for most software and AI development processes, we argue that for some highly capable foundation models likely to be developed in the near future, open-sourcing may pose sufficiently extreme risks to outweigh the benefits. In such a case, highly capable foundation models should not be open-sourced, at least not initially. Alternative strategies, including non-open-source model sharing options, are explored. The paper concludes with recommendations for developers, standard-setting bodies, and governments for establishing safe and responsible model sharing practices and preserving open-source benefits where safe.

cs.CY↗
arXiv2023

Probabilistic Contraction Analysis of Iterated Random Operators

In many branches of engineering, Banach contraction mapping theorem is employed to establish the convergence of certain deterministic algorithms. Randomized versions of these algorithms have been developed that have proved useful in data-driven problems. In a class of randomized algorithms, in each iteration, the contraction map is approximated with an operator that uses independent and identically distributed samples of certain random variables. This leads to iterated random operators acting on an initial point in a complete metric space, and it generates a Markov chain. In this paper, we develop a new stochastic dominance based proof technique, called probabilistic contraction analysis, for establishing the convergence in probability of Markov chains generated by such iterated random operators in certain limiting regime. The methods developed in this paper provides a general framework for understanding convergence of a wide variety of Monte Carlo methods in which contractive property is present. We apply the convergence result to conclude the convergence of fitted value iteration and fitted relative value iteration in continuous state and continuous action Markov decision problems as representative applications of the general framework developed here.

math.PR↗
arXiv2023

A Deep Reinforcement Learning Framework for Eco-driving in Connected and Automated Hybrid Electric Vehicles

Connected and Automated Vehicles (CAVs), in particular those with multiple power sources, have the potential to significantly reduce fuel consumption and travel time in real-world driving conditions. In particular, the Eco-driving problem seeks to design optimal speed and power usage profiles based upon look-ahead information from connectivity and advanced mapping features, to minimize the fuel consumption over a given itinerary. In this work, the Eco-driving problem is formulated as a Partially Observable Markov Decision Process (POMDP), which is then solved with a state-of-art Deep Reinforcement Learning (DRL) Actor Critic algorithm, Proximal Policy Optimization. An Eco-driving simulation environment is developed for training and evaluation purposes. To benchmark the performance of the DRL controller, a baseline controller representing the human driver, a trajectory optimization algorithm and the wait-and-see deterministic optimal solution are presented. With a minimal onboard computational requirement and a comparable travel time, the DRL controller reduces the fuel consumption by more than 17% compared against the baseline controller by modulating the vehicle velocity over the route and performing energy-efficient approach and departure at signalized intersections, over-performing the more computationally demanding trajectory optimization method

eess.SY↗
arXiv2023

Guiding Pretraining in Reinforcement Learning with Large Language Models

Reinforcement learning algorithms typically struggle in the absence of a dense, well-shaped reward function. Intrinsically motivated exploration methods address this limitation by rewarding agents for visiting novel states or transitions, but these methods offer limited benefits in large environments where most discovered novelty is irrelevant for downstream tasks. We describe a method that uses background knowledge from text corpora to shape exploration. This method, called ELLM (Exploring with LLMs) rewards an agent for achieving goals suggested by a language model prompted with a description of the agent's current state. By leveraging large-scale language model pretraining, ELLM guides agents toward human-meaningful and plausibly useful behaviors without requiring a human in the loop. We evaluate ELLM in the Crafter game environment and the Housekeep robotic simulator, showing that ELLM-trained agents have better coverage of common-sense behaviors during pretraining and usually match or improve performance on a range of downstream tasks. Code available at https://github.com/yuqingd/ellm.

cs.LG↗
arXiv2023

REBOOT: Reuse Data for Bootstrapping Efficient Real-World Dexterous Manipulation

Dexterous manipulation tasks involving contact-rich interactions pose a significant challenge for both model-based control systems and imitation learning algorithms. The complexity arises from the need for multi-fingered robotic hands to dynamically establish and break contacts, balance non-prehensile forces, and control large degrees of freedom. Reinforcement learning (RL) offers a promising approach due to its general applicability and capacity to autonomously acquire optimal manipulation strategies. However, its real-world application is often hindered by the necessity to generate a large number of samples, reset the environment, and obtain reward signals. In this work, we introduce an efficient system for learning dexterous manipulation skills with RL to alleviate these challenges. The main idea of our approach is the integration of recent advances in sample-efficient RL and replay buffer bootstrapping. This combination allows us to utilize data from different tasks or objects as a starting point for training new tasks, significantly improving learning efficiency. Additionally, our system completes the real-world training cycle by incorporating learned resets via an imitation-based pickup policy as well as learned reward functions, eliminating the need for manual resets and reward engineering. We demonstrate the benefits of reusing past data as replay buffer initialization for new tasks, for instance, the fast acquisition of intricate manipulation skills in the real world on a four-fingered robotic hand. (Videos: https://sites.google.com/view/reboot-dexterous)

cs.LG↗
arXiv2023

Masquerade: Simple and Lightweight Transaction Reordering Mitigation in Blockchains

Blockchains offer strong security gurarantees, but cannot protect users against the ordering of transactions. Players such as miners, bots and validators can reorder various transactions and reap significant profits, called the Maximal Extractable Value (MEV). In this paper, we propose an MEV aware protocol design called Masquerade, and show that it will increase user satisfaction and confidence in the system. We propose a strict per-transaction level of ordering to ensure that a transaction is committed either way even if it is revealed. In this protocol, we introduce the notion of a "token" to mitigate the actions taken by an adversary in an attack scenario. Such tokens can be purchased voluntarily by users, who can then choose to include the token numbers in their transactions. If the users include the token in their transactions, then our protocol requires the block-builder to order the transactions strictly according to token numbers. We show through extensive simulations that this reduces the probability that the adversaries can benefit from MEV transactions as compared to existing current practices.

cs.CR↗
arXiv2023

Tackling Combinatorial Distribution Shift: A Matrix Completion Perspective

Obtaining rigorous statistical guarantees for generalization under distribution shift remains an open and active research area. We study a setting we call combinatorial distribution shift, where (a) under the test- and training-distributions, the labels $z$ are determined by pairs of features $(x,y)$, (b) the training distribution has coverage of certain marginal distributions over $x$ and $y$ separately, but (c) the test distribution involves examples from a product distribution over $(x,y)$ that is {not} covered by the training distribution. Focusing on the special case where the labels are given by bilinear embeddings into a Hilbert space $H$: $\mathbb{E}[z \mid x,y ]=\langle f_{\star}(x),g_{\star}(y)\rangle_{H}$, we aim to extrapolate to a test distribution domain that is $not$ covered in training, i.e., achieving bilinear combinatorial extrapolation. Our setting generalizes a special case of matrix completion from missing-not-at-random data, for which all existing results require the ground-truth matrices to be either exactly low-rank, or to exhibit very sharp spectral cutoffs. In this work, we develop a series of theoretical results that enable bilinear combinatorial extrapolation under gradual spectral decay as observed in typical high-dimensional data, including novel algorithms, generalization guarantees, and linear-algebraic results. A key tool is a novel perturbation bound for the rank-$k$ singular value decomposition approximations between two matrices that depends on the relative spectral gap rather than the absolute spectral gap, a result that may be of broader independent interest.

cs.LG↗
arXiv2023

Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop Feedback

Exploration and reward specification are fundamental and intertwined challenges for reinforcement learning. Solving sequential decision-making tasks requiring expansive exploration requires either careful design of reward functions or the use of 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 present a technique called Human Guided Exploration (HuGE), which uses low-quality feedback from non-expert users that may be sporadic, asynchronous, and noisy. HuGE guides exploration for reinforcement learning not only in simulation but also in the real world, all without meticulous reward specification. The key concept involves bifurcating human feedback and policy learning: human feedback steers exploration, while self-supervised learning from the exploration data yields unbiased policies. This procedure can leverage noisy, asynchronous human feedback to learn policies with no hand-crafted reward design or exploration bonuses. 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, using occasional, asynchronous feedback from human supervisors.

cs.LG↗
arXiv2023

Distributionally Adaptive Meta Reinforcement Learning

Meta-reinforcement learning algorithms provide a data-driven way to acquire policies that quickly adapt to many tasks with varying rewards or dynamics functions. However, learned meta-policies are often effective only on the exact task distribution on which they were trained and struggle in the presence of distribution shift of test-time rewards or transition dynamics. In this work, we develop a framework for meta-RL algorithms that are able to behave appropriately under test-time distribution shifts in the space of tasks. Our framework centers on an adaptive approach to distributional robustness that trains a population of meta-policies to be robust to varying levels of distribution shift. When evaluated on a potentially shifted test-time distribution of tasks, this allows us to choose the meta-policy with the most appropriate level of robustness, and use it to perform fast adaptation. We formally show how our framework allows for improved regret under distribution shift, and empirically show its efficacy on simulated robotics problems under a wide range of distribution shifts.

cs.LG↗
arXiv2023

Cobalt: Optimizing Mining Rewards in Proof-of-Work Network Games

Mining in proof-of-work blockchains has become an expensive affair requiring specialized hardware capable of executing several megahashes per second at huge electricity costs. Miners earn a reward each time they mine a block within the longest chain, which helps offset their mining costs. It is therefore of interest to miners to maximize the number of mined blocks in the blockchain and increase revenue. A key factor affecting mining rewards earned is the connectivity between miners in the peer-to-peer network. To maximize rewards a miner must choose its network connections carefully, ensuring existence of paths to other miners that are on average of a lower latency compared to paths between other miners. We formulate the problem of deciding whom to connect to for miners as a combinatorial bandit problem. Each node picks its neighbors strategically to minimize the latency to reach 90\% of the hash power of the network relative to the 90-th percentile latency from other nodes. A key contribution of our work is the use of a network coordinates based model for learning the network structure within the bandit algorithm. Experimentally we show our proposed algorithm outperforming or matching baselines on diverse network settings.

cs.NI↗
arXiv2023

Cherry-Picking with Reinforcement Learning : Robust Dynamic Grasping in Unstable Conditions

Grasping small objects surrounded by unstable or non-rigid material plays a crucial role in applications such as surgery, harvesting, construction, disaster recovery, and assisted feeding. This task is especially difficult when fine manipulation is required in the presence of sensor noise and perception errors; errors inevitably trigger dynamic motion, which is challenging to model precisely. Circumventing the difficulty to build accurate models for contacts and dynamics, data-driven methods like reinforcement learning (RL) can optimize task performance via trial and error, reducing the need for accurate models of contacts and dynamics. Applying RL methods to real robots, however, has been hindered by factors such as prohibitively high sample complexity or the high training infrastructure cost for providing resets on hardware. This work presents CherryBot, an RL system that uses chopsticks for fine manipulation that surpasses human reactiveness for some dynamic grasping tasks. By integrating imprecise simulators, suboptimal demonstrations and external state estimation, we study how to make a real-world robot learning system sample efficient and general while reducing the human effort required for supervision. Our system shows continual improvement through 30 minutes of real-world interaction: through reactive retry, it achieves an almost 100% success rate on the demanding task of using chopsticks to grasp small objects swinging in the air. We demonstrate the reactiveness, robustness and generalizability of CherryBot to varying object shapes and dynamics (e.g., external disturbances like wind and human perturbations). Videos are available at https://goodcherrybot.github.io/.

cs.RO↗
arXiv2023

Empirical Measurement of Aesthetic Experience of Music

Chills or goosebumps, also called frisson, is a phenomenon that is often associated with an aesthetic experience e.g., music or some other ecstatic experience. The temporal and spatial cause of frisson in the brain has been one of the biggest mysteries of human nature. Accumulating evidence suggests that aesthetic, namely subjective, affective, and evaluative processes are at play while listening to music, hence, it is an important subjective stimulus for systematic investigation. Advances in neuroimaging and cognitive neuroscience, have given impetus to neuro-aesthetics, a novel approach to music providing a phenomenological brain-based framework for the aesthetic experience of music with the potential to open the scope for future research. In this paper, we present an affordable, wearable, easy-to-carry device to measure phenomenological goosebumps intensity on our skin with respect to real-time data using IoT devices (Raspberry pi 3, model B). To test the device subjects were asked to provide a list of songs that elicit goosebumps. Wireless earphones were provided, allowing participants to walk around and dance while listening to their music. (Some subjects moved during sessions). Results indicate that goosebumps were reliably detected by the device after visual inspection of the videos/music. The effective measurement when interfaced with neurophysiological devices such as electroencephalography (EEG) can help interpret biomarkers of ecstatic emotions. The second part of the study focuses on identifying primary brain regions involved in goosebump experience during musical stimulation.

cs.HC↗