arXiv subjects

Abhishek Gupta

Publications and source records attributed to Abhishek Gupta.

At least 235 records · Page 13Linked to original sources

arXiv2020

On the Coverage Performance of Boolean-Poisson Cluster Models for Wireless Sensor Networks

In this paper, we consider wireless sensor networks (WSNs) with sensor nodes exhibiting clustering in their deployment. We model the coverage region of such WSNs by Boolean Poisson cluster models (BPCM) where sensors nodes' location is according to a Poisson cluster process (PCP) and each sensor has an independent sensing range around it. We consider two variants of PCP, in particular \matern and Thomas cluster process to form Boolean \matern and Thomas cluster models. We first derive the capacity functional of these models. Using the derived expressions, we compute the sensing probability of an event and compare it with sensing probability of a WSN modeled by a Boolean Poisson model where sensors are deployed according to a Poisson point process. We also derive the power required for each cluster to collect data from all of its sensors for the three considered WSNs. We show that a BPCM WSN has less power requirement in comparison to the Boolean Poisson WSN, but it suffers from lower coverage, leading to a trade-off between per-cluster power requirement and the sensing performance. A cluster process with desired clustering may provide better coverage while maintaining low power requirements.

cs.IT↗

arXiv2020

BISTRO: Berkeley Integrated System for Transportation Optimization

This article introduces BISTRO, a new open source transportation planning decision support system that uses an agent-based simulation and optimization approach to anticipate and develop adaptive plans for possible technological disruptions and growth scenarios. The new framework was evaluated in the context of a machine learning competition hosted within Uber Technologies, Inc., in which over 400 engineers and data scientists participated. For the purposes of this competition, a benchmark model, based on the city of Sioux Falls, South Dakota, was adapted to the BISTRO framework. An important finding of this study was that in spite of rigorous analysis and testing done prior to the competition, the two top-scoring teams discovered an unbounded region of the search space, rendering the solutions largely uninterpretable for the purposes of decision-support. On the other hand, a follow-on study aimed to fix the objective function, served to demonstrate BISTRO's utility as a human-in-the-loop cyberphysical system: one that uses scenario-based optimization algorithms as a feedback mechanism to assist urban planners with iteratively refining objective function and constraints specification on intervention strategies such that the portfolio of transportation intervention strategy alternatives eventually chosen achieves high-level regional planning goals developed through participatory stakeholder engagement practices.

cs.CY↗

arXiv2019

ROBEL: Robotics Benchmarks for Learning with Low-Cost Robots

ROBEL is an open-source platform of cost-effective robots designed for reinforcement learning in the real world. ROBEL introduces two robots, each aimed to accelerate reinforcement learning research in different task domains: D'Claw is a three-fingered hand robot that facilitates learning dexterous manipulation tasks, and D'Kitty is a four-legged robot that facilitates learning agile legged locomotion tasks. These low-cost, modular robots are easy to maintain and are robust enough to sustain on-hardware reinforcement learning from scratch with over 14000 training hours registered on them to date. To leverage this platform, we propose an extensible set of continuous control benchmark tasks for each robot. These tasks feature dense and sparse task objectives, and additionally introduce score metrics as hardware-safety. We provide benchmark scores on an initial set of tasks using a variety of learning-based methods. Furthermore, we show that these results can be replicated across copies of the robots located in different institutions. Code, documentation, design files, detailed assembly instructions, final policies, baseline details, task videos, and all supplementary materials required to reproduce the results are available at www.roboticsbenchmarks.org.

cs.RO↗

arXiv2019

Unsupervised Curricula for Visual Meta-Reinforcement Learning

In principle, meta-reinforcement learning algorithms leverage experience across many tasks to learn fast reinforcement learning (RL) strategies that transfer to similar tasks. However, current meta-RL approaches rely on manually-defined distributions of training tasks, and hand-crafting these task distributions can be challenging and time-consuming. Can "useful" pre-training tasks be discovered in an unsupervised manner? We develop an unsupervised algorithm for inducing an adaptive meta-training task distribution, i.e. an automatic curriculum, by modeling unsupervised interaction in a visual environment. The task distribution is scaffolded by a parametric density model of the meta-learner's trajectory distribution. We formulate unsupervised meta-RL as information maximization between a latent task variable and the meta-learner's data distribution, and describe a practical instantiation which alternates between integration of recent experience into the task distribution and meta-learning of the updated tasks. Repeating this procedure leads to iterative reorganization such that the curriculum adapts as the meta-learner's data distribution shifts. In particular, we show how discriminative clustering for visual representation can support trajectory-level task acquisition and exploration in domains with pixel observations, avoiding pitfalls of alternatives. In experiments on vision-based navigation and manipulation domains, we show that the algorithm allows for unsupervised meta-learning that transfers to downstream tasks specified by hand-crafted reward functions and serves as pre-training for more efficient supervised meta-learning of test task distributions.

cs.AI↗

arXiv2019

A Multi-Task Gradient Descent Method for Multi-Label Learning

Multi-label learning studies the problem where an instance is associated with a set of labels. By treating single-label learning problem as one task, the multi-label learning problem can be casted as solving multiple related tasks simultaneously. In this paper, we propose a novel Multi-task Gradient Descent (MGD) algorithm to solve a group of related tasks simultaneously. In the proposed algorithm, each task minimizes its individual cost function using reformative gradient descent, where the relations among the tasks are facilitated through effectively transferring model parameter values across multiple tasks. Theoretical analysis shows that the proposed algorithm is convergent with a proper transfer mechanism. Compared with the existing approaches, MGD is easy to implement, has less requirement on the training model, can achieve seamless asymmetric transformation such that negative transfer is mitigated, and can benefit from parallel computing when the number of tasks is large. The competitive experimental results on multi-label learning datasets validate the effectiveness of the proposed algorithm.

cs.LG↗

arXiv2019

Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning

We present relay policy learning, a method for imitation and reinforcement learning that can solve multi-stage, long-horizon robotic tasks. This general and universally-applicable, two-phase approach consists of an imitation learning stage that produces goal-conditioned hierarchical policies, and a reinforcement learning phase that finetunes these policies for task performance. Our method, while not necessarily perfect at imitation learning, is very amenable to further improvement via environment interaction, allowing it to scale to challenging long-horizon tasks. We simplify the long-horizon policy learning problem by using a novel data-relabeling algorithm for learning goal-conditioned hierarchical policies, where the low-level only acts for a fixed number of steps, regardless of the goal achieved. While we rely on demonstration data to bootstrap policy learning, we do not assume access to demonstrations of every specific tasks that is being solved, and instead leverage unstructured and unsegmented demonstrations of semantically meaningful behaviors that are not only less burdensome to provide, but also can greatly facilitate further improvement using reinforcement learning. We demonstrate the effectiveness of our method on a number of multi-stage, long-horizon manipulation tasks in a challenging kitchen simulation environment. Videos are available at https://relay-policy-learning.github.io/

cs.LG↗

arXiv2019

Distributed SGD Generalizes Well Under Asynchrony

The performance of fully synchronized distributed systems has faced a bottleneck due to the big data trend, under which asynchronous distributed systems are becoming a major popularity due to their powerful scalability. In this paper, we study the generalization performance of stochastic gradient descent (SGD) on a distributed asynchronous system. The system consists of multiple worker machines that compute stochastic gradients which are further sent to and aggregated on a common parameter server to update the variables, and the communication in the system suffers from possible delays. Under the algorithm stability framework, we prove that distributed asynchronous SGD generalizes well given enough data samples in the training optimization. In particular, our results suggest to reduce the learning rate as we allow more asynchrony in the distributed system. Such adaptive learning rate strategy improves the stability of the distributed algorithm and reduces the corresponding generalization error. Then, we confirm our theoretical findings via numerical experiments.

stat.ML↗

arXiv2019

Canada Protocol: an ethical checklist for the use of Artificial Intelligence in Suicide Prevention and Mental Health

Introduction: To improve current public health strategies in suicide prevention and mental health, governments, researchers and private companies increasingly use information and communication technologies, and more specifically Artificial Intelligence and Big Data. These technologies are promising but raise ethical challenges rarely covered by current legal systems. It is essential to better identify, and prevent potential ethical risks. Objectives: The Canada Protocol - MHSP is a tool to guide and support professionals, users, and researchers using AI in mental health and suicide prevention. Methods: A checklist was constructed based upon ten international reports on AI and ethics and two guides on mental health and new technologies. 329 recommendations were identified, of which 43 were considered as applicable to Mental Health and AI. The checklist was validated, using a two round Delphi Consultation. Results: 16 experts participated in the first round of the Delphi Consultation and 8 participated in the second round. Of the original 43 items, 38 were retained. They concern five categories: "Description of the Autonomous Intelligent System" (n=8), "Privacy and Transparency" (n=8), "Security" (n=6), "Health-Related Risks" (n=8), "Biases" (n=8). The checklist was considered relevant by most users, and could need versions tailored to each category of target users.

cs.CY↗

arXiv2019

Learning latent state representation for speeding up exploration

Exploration is an extremely challenging problem in reinforcement learning, especially in high dimensional state and action spaces and when only sparse rewards are available. Effective representations can indicate which components of the state are task relevant and thus reduce the dimensionality of the space to explore. In this work, we take a representation learning viewpoint on exploration, utilizing prior experience to learn effective latent representations, which can subsequently indicate which regions to explore. Prior experience on separate but related tasks help learn representations of the state which are effective at predicting instantaneous rewards. These learned representations can then be used with an entropy-based exploration method to effectively perform exploration in high dimensional spaces by effectively lowering the dimensionality of the search space. We show the benefits of this representation for meta-exploration in a simulated object pushing environment.

cs.LG↗

arXiv2019

Automatically Composing Representation Transformations as a Means for Generalization

A generally intelligent learner should generalize to more complex tasks than it has previously encountered, but the two common paradigms in machine learning -- either training a separate learner per task or training a single learner for all tasks -- both have difficulty with such generalization because they do not leverage the compositional structure of the task distribution. This paper introduces the compositional problem graph as a broadly applicable formalism to relate tasks of different complexity in terms of problems with shared subproblems. We propose the compositional generalization problem for measuring how readily old knowledge can be reused and hence built upon. As a first step for tackling compositional generalization, we introduce the compositional recursive learner, a domain-general framework for learning algorithmic procedures for composing representation transformations, producing a learner that reasons about what computation to execute by making analogies to previously seen problems. We show on a symbolic and a high-dimensional domain that our compositional approach can generalize to more complex problems than the learner has previously encountered, whereas baselines that are not explicitly compositional do not.

cs.LG↗

arXiv2019

Domain Randomization for Active Pose Estimation

Accurate state estimation is a fundamental component of robotic control. In robotic manipulation tasks, as is our focus in this work, state estimation is essential for identifying the positions of objects in the scene, forming the basis of the manipulation plan. However, pose estimation typically requires expensive 3D cameras or additional instrumentation such as fiducial markers to perform accurately. Recently, Tobin et al.~introduced an approach to pose estimation based on domain randomization, where a neural network is trained to predict pose directly from a 2D image of the scene. The network is trained on computer-generated images with a high variation in textures and lighting, thereby generalizing to real-world images. In this work, we investigate how to improve the accuracy of domain randomization based pose estimation. Our main idea is that active perception -- moving the robot to get a better estimate of pose -- can be trained in simulation and transferred to real using domain randomization. In our approach, the robot trains in a domain-randomized simulation how to estimate pose from a \emph{sequence} of images. We show that our approach can significantly improve the accuracy of standard pose estimation in several scenarios: when the robot holding an object moves, when reference objects are moved in the scene, or when the camera is moved around the object.

cs.CV↗

arXiv2019

Learning Actionable Representations with Goal-Conditioned Policies

Representation learning is a central challenge across a range of machine learning areas. In reinforcement learning, effective and functional representations have the potential to tremendously accelerate learning progress and solve more challenging problems. Most prior work on representation learning has focused on generative approaches, learning representations that capture all underlying factors of variation in the observation space in a more disentangled or well-ordered manner. In this paper, we instead aim to learn functionally salient representations: representations that are not necessarily complete in terms of capturing all factors of variation in the observation space, but rather aim to capture those factors of variation that are important for decision making -- that are "actionable." These representations are aware of the dynamics of the environment, and capture only the elements of the observation that are necessary for decision making rather than all factors of variation, without explicit reconstruction of the observation. We show how these representations can be useful to improve exploration for sparse reward problems, to enable long horizon hierarchical reinforcement learning, and as a state representation for learning policies for downstream tasks. We evaluate our method on a number of simulated environments, and compare it to prior methods for representation learning, exploration, and hierarchical reinforcement learning.

cs.LG↗

arXiv2019

Guiding Policies with Language via Meta-Learning

Behavioral skills or policies for autonomous agents are conventionally learned from reward functions, via reinforcement learning, or from demonstrations, via imitation learning. However, both modes of task specification have their disadvantages: reward functions require manual engineering, while demonstrations require a human expert to be able to actually perform the task in order to generate the demonstration. Instruction following from natural language instructions provides an appealing alternative: in the same way that we can specify goals to other humans simply by speaking or writing, we would like to be able to specify tasks for our machines. However, a single instruction may be insufficient to fully communicate our intent or, even if it is, may be insufficient for an autonomous agent to actually understand how to perform the desired task. In this work, we propose an interactive formulation of the task specification problem, where iterative language corrections are provided to an autonomous agent, guiding it in acquiring the desired skill. Our proposed language-guided policy learning algorithm can integrate an instruction and a sequence of corrections to acquire new skills very quickly. In our experiments, we show that this method can enable a policy to follow instructions and corrections for simulated navigation and manipulation tasks, substantially outperforming direct, non-interactive instruction following.

cs.LG↗

arXiv2019

Soft Actor-Critic Algorithms and Applications

Model-free deep reinforcement learning (RL) algorithms have been successfully applied to a range of challenging sequential decision making and control tasks. However, these methods typically suffer from two major challenges: high sample complexity and brittleness to hyperparameters. Both of these challenges limit the applicability of such methods to real-world domains. In this paper, we describe Soft Actor-Critic (SAC), our recently introduced off-policy actor-critic algorithm based on the maximum entropy RL framework. In this framework, the actor aims to simultaneously maximize expected return and entropy. That is, to succeed at the task while acting as randomly as possible. We extend SAC to incorporate a number of modifications that accelerate training and improve stability with respect to the hyperparameters, including a constrained formulation that automatically tunes the temperature hyperparameter. We systematically evaluate SAC on a range of benchmark tasks, as well as real-world challenging tasks such as locomotion for a quadrupedal robot and robotic manipulation with a dexterous hand. With these improvements, SAC achieves state-of-the-art performance, outperforming prior on-policy and off-policy methods in sample-efficiency and asymptotic performance. Furthermore, we demonstrate that, in contrast to other off-policy algorithms, our approach is very stable, achieving similar performance across different random seeds. These results suggest that SAC is a promising candidate for learning in real-world robotics tasks.

cs.LG↗

arXiv2019

AIR5: Five Pillars of Artificial Intelligence Research

In this article, we provide and overview of what we consider to be some of the most pressing research questions facing the fields of artificial intelligence (AI) and computational intelligence (CI); with the latter focusing on algorithms that are inspired by various natural phenomena. We demarcate these questions using five unique Rs - namely, (i) rationalizability, (ii) resilience, (iii) reproducibility, (iv) realism, and (v) responsibility. Notably, just as air serves as the basic element of biological life, the term AIR5 - cumulatively referring to the five aforementioned Rs - is introduced herein to mark some of the basic elements of artificial life (supporting the sustained growth of AI and CI). A brief summary of each of the Rs is presented, highlighting their relevance as pillars of future research in this arena.

cs.AI↗

arXiv2018

Auctioning Electricity under Deep Renewable Integration using a Penalty for Shortfall

We analyze the problem of a renewable generator who wants to sell its random generation in a two-stage market to a number of strategic, but flexible, load serving entities (LSEs). To offer an incentive to participate in the auction, the generator promises to pay a penalty associated with any shortfall in generation due to the uncertain nature of the traded resource. We devise an auction mechanism that efficiently allocates electricity among LSEs while eliciting their true valuations. We show that the consumer surplus of the LSEs and expected profit of the generator are positive, thereby creating a win-win situation for all market participants.

eess.SY↗

arXiv2018

Modeling and Analysis of Wildfire Detection using Wireless Sensor Network with Poisson Deployment

In many forest fire incidences, late detection of the fire has lead to severe damages to the forest and human property requiring more resources to gain control over the fire. An early warning and immediate response system can be a promising solution to avoid such massive losses. This paper considers a network consisting of multiple wireless sensors randomly deployed throughout the forest for early prompt detection of fire. We present a framework to model fire propagation in a forest and analyze the performance of considered wireless sensor network in terms of fire detection probability. In particular, this paper models sensor deployment as a Poisson point process (PPP) and models the forest fire as a dynamic event which expands with time. We also present various insights to the system including required sensor density and impact of wind velocity on the detection performance. We show that larger wind velocity may not necessarily imply bad sensing performance or the requirement of a denser deployment.

eess.SP↗

arXiv2018

Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low-Cost

Dexterous multi-fingered robotic hands can perform a wide range of manipulation skills, making them an appealing component for general-purpose robotic manipulators. However, such hands pose a major challenge for autonomous control, due to the high dimensionality of their configuration space and complex intermittent contact interactions. In this work, we propose deep reinforcement learning (deep RL) as a scalable solution for learning complex, contact rich behaviors with multi-fingered hands. Deep RL provides an end-to-end approach to directly map sensor readings to actions, without the need for task specific models or policy classes. We show that contact-rich manipulation behavior with multi-fingered hands can be learned by directly training with model-free deep RL algorithms in the real world, with minimal additional assumption and without the aid of simulation. We learn a variety of complex behaviors on two different low-cost hardware platforms. We show that each task can be learned entirely from scratch, and further study how the learning process can be further accelerated by using a small number of human demonstrations to bootstrap learning. Our experiments demonstrate that complex multi-fingered manipulation skills can be learned in the real world in about 4-7 hours for most tasks, and that demonstrations can decrease this to 2-3 hours, indicating that direct deep RL training in the real world is a viable and practical alternative to simulation and model-based control. \url{https://sites.google.com/view/deeprl-handmanipulation}

cs.AI↗