arXiv subjects

Abhishek Gupta

Publications and source records attributed to Abhishek Gupta.

At least 253 records · Page 14Linked to original sources

arXiv2018

Diversity is All You Need: Learning Skills without a Reward Function

Intelligent creatures can explore their environments and learn useful skills without supervision. In this paper, we propose DIAYN ('Diversity is All You Need'), a method for learning useful skills without a reward function. Our proposed method learns skills by maximizing an information theoretic objective using a maximum entropy policy. On a variety of simulated robotic tasks, we show that this simple objective results in the unsupervised emergence of diverse skills, such as walking and jumping. In a number of reinforcement learning benchmark environments, our method is able to learn a skill that solves the benchmark task despite never receiving the true task reward. We show how pretrained skills can provide a good parameter initialization for downstream tasks, and can be composed hierarchically to solve complex, sparse reward tasks. Our results suggest that unsupervised discovery of skills can serve as an effective pretraining mechanism for overcoming challenges of exploration and data efficiency in reinforcement learning.

cs.AI↗

arXiv2018

Adversarial Reinforcement Learning for Observer Design in Autonomous Systems under Cyber Attacks

Complex autonomous control systems are subjected to sensor failures, cyber-attacks, sensor noise, communication channel failures, etc. that introduce errors in the measurements. The corrupted information, if used for making decisions, can lead to degraded performance. We develop a framework for using adversarial deep reinforcement learning to design observer strategies that are robust to adversarial errors in information channels. We further show through simulation studies that the learned observation strategies perform remarkably well when the adversary's injected errors are bounded in some sense. We use neural network as function approximator in our studies with the understanding that any other suitable function approximating class can be used within our framework.

cs.LG↗

arXiv2018

Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations

Dexterous multi-fingered hands are extremely versatile and provide a generic way to perform a multitude of tasks in human-centric environments. However, effectively controlling them remains challenging due to their high dimensionality and large number of potential contacts. Deep reinforcement learning (DRL) provides a model-agnostic approach to control complex dynamical systems, but has not been shown to scale to high-dimensional dexterous manipulation. Furthermore, deployment of DRL on physical systems remains challenging due to sample inefficiency. Consequently, the success of DRL in robotics has thus far been limited to simpler manipulators and tasks. In this work, we show that model-free DRL can effectively scale up to complex manipulation tasks with a high-dimensional 24-DoF hand, and solve them from scratch in simulated experiments. Furthermore, with the use of a small number of human demonstrations, the sample complexity can be significantly reduced, which enables learning with sample sizes equivalent to a few hours of robot experience. The use of demonstrations result in policies that exhibit very natural movements and, surprisingly, are also substantially more robust.

cs.LG↗

arXiv2018

Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation

Imitation learning is an effective approach for autonomous systems to acquire control policies when an explicit reward function is unavailable, using supervision provided as demonstrations from an expert, typically a human operator. However, standard imitation learning methods assume that the agent receives examples of observation-action tuples that could be provided, for instance, to a supervised learning algorithm. This stands in contrast to how humans and animals imitate: we observe another person performing some behavior and then figure out which actions will realize that behavior, compensating for changes in viewpoint, surroundings, object positions and types, and other factors. We term this kind of imitation learning "imitation-from-observation," and propose an imitation learning method based on video prediction with context translation and deep reinforcement learning. This lifts the assumption in imitation learning that the demonstration should consist of observations in the same environment configuration, and enables a variety of interesting applications, including learning robotic skills that involve tool use simply by observing videos of human tool use. Our experimental results show the effectiveness of our approach in learning a wide range of real-world robotic tasks modeled after common household chores from videos of a human demonstrator, including sweeping, ladling almonds, pushing objects as well as a number of tasks in simulation.

cs.LG↗

arXiv2018

Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings

In this work, we take a representation learning perspective on hierarchical reinforcement learning, where the problem of learning lower layers in a hierarchy is transformed into the problem of learning trajectory-level generative models. We show that we can learn continuous latent representations of trajectories, which are effective in solving temporally extended and multi-stage problems. Our proposed model, SeCTAR, draws inspiration from variational autoencoders, and learns latent representations of trajectories. A key component of this method is to learn both a latent-conditioned policy and a latent-conditioned model which are consistent with each other. Given the same latent, the policy generates a trajectory which should match the trajectory predicted by the model. This model provides a built-in prediction mechanism, by predicting the outcome of closed loop policy behavior. We propose a novel algorithm for performing hierarchical RL with this model, combining model-based planning in the learned latent space with an unsupervised exploration objective. We show that our model is effective at reasoning over long horizons with sparse rewards for several simulated tasks, outperforming standard reinforcement learning methods and prior methods for hierarchical reasoning, model-based planning, and exploration.

cs.LG↗

arXiv2018

Virtual-Mobile-Core Placement for Metro Network

Traditional highly-centralized mobile core networks (e.g., Evolved Packet Core (EPC)) need to be constantly upgraded both in their network functions and backhaul links, to meet increasing traffic demands. Network Function Virtualization (NFV) is being investigated as a potential cost-effective solution for this upgrade. A virtual mobile core (here, virtual EPC, vEPC) provides deployment flexibility and scalability while reducing costs, network-resource consumption and application delay. Moreover, a distributed deployment of vEPC is essential for emerging paradigms like Multi-Access Edge Computing (MEC). In this work, we show that significant reduction in networkresource consumption can be achieved as a result of optimal placement of vEPC functions in metro area. Further, we show that not all vEPC functions need to be distributed. In our study, for the first time, we account for vEPC interactions in both data and control planes (Non-Access Stratum (NAS) signaling procedure Service Chains (SCs) with application latency requirements) using a detailed mathematical model.

cs.NI↗

arXiv2018

Meta-Reinforcement Learning of Structured Exploration Strategies

Exploration is a fundamental challenge in reinforcement learning (RL). Many of the current exploration methods for deep RL use task-agnostic objectives, such as information gain or bonuses based on state visitation. However, many practical applications of RL involve learning more than a single task, and prior tasks can be used to inform how exploration should be performed in new tasks. In this work, we explore how prior tasks can inform an agent about how to explore effectively in new situations. We introduce a novel gradient-based fast adaptation algorithm -- model agnostic exploration with structured noise (MAESN) -- to learn exploration strategies from prior experience. The prior experience is used both to initialize a policy and to acquire a latent exploration space that can inject structured stochasticity into a policy, producing exploration strategies that are informed by prior knowledge and are more effective than random action-space noise. We show that MAESN is more effective at learning exploration strategies when compared to prior meta-RL methods, RL without learned exploration strategies, and task-agnostic exploration methods. We evaluate our method on a variety of simulated tasks: locomotion with a wheeled robot, locomotion with a quadrupedal walker, and object manipulation.

cs.LG↗

arXiv2017

Addressing Expensive Multi-objective Games with Postponed Preference Articulation via Memetic Co-evolution

This paper presents algorithmic and empirical contributions demonstrating that the convergence characteristics of a co-evolutionary approach to tackle Multi-Objective Games (MOGs) with postponed preference articulation can often be hampered due to the possible emergence of the so-called Red Queen effect. Accordingly, it is hypothesized that the convergence characteristics can be significantly improved through the incorporation of memetics (local solution refinements as a form of lifelong learning), as a promising means of mitigating (or at least suppressing) the Red Queen phenomenon by providing a guiding hand to the purely genetic mechanisms of co-evolution. Our practical motivation is to address MOGs of a time-sensitive nature that are characterized by computationally expensive evaluations, wherein there is a natural need to reduce the total number of true function evaluations consumed in achieving good quality solutions. To this end, we propose novel enhancements to co-evolutionary approaches for tackling MOGs, such that memetic local refinements can be efficiently applied on evolved candidate strategies by searching on computationally cheap surrogate payoff landscapes (that preserve postponed preference conditions). The efficacy of the proposal is demonstrated on a suite of test MOGs that have been designed.

cs.NE↗

arXiv2017

A Scalable Approach for Service Chain (SC) Mapping with Multiple SC Instances in a Wide-Area Network

Network Function Virtualization (NFV) aims to simplify deployment of network services by running Virtual Network Functions (VNFs) on commercial off-the-shelf servers. Service deployment involves placement of VNFs and in-sequence routing of traffic flows through VNFs comprising a Service Chain (SC). The joint VNF placement and traffic routing is called SC mapping. In a Wide-Area Network (WAN), a situation may arise where several traffic flows, generated by many distributed node pairs, require the same SC; then, a single instance (or occurrence) of that SC might not be enough. SC mapping with multiple SC instances for the same SC turns out to be a very complex problem, since the sequential traversal of VNFs has to be maintained while accounting for traffic flows in various directions. Our study is the first to deal with the problem of SC mapping with multiple SC instances to minimize network resource consumption. We first propose an Integer Linear Program (ILP) to solve this problem. Since ILP does not scale to large networks, we develop a column-generation-based ILP (CG-ILP) model. However, we find that exact mathematical modeling of the problem results in quadratic constraints in our CG-ILP. The quadratic constraints are made linear but even the scalability of CG-ILP is limited. Hence, we also propose a two-phase column-generation-based approach to get results over large network topologies within reasonable computational times. Using such an approach, we observe that an appropriate choice of only a small set of SC instances can lead to a solution very close to the minimum bandwidth consumption. Further, this approach also helps us to analyze the effects of number of VNF replicas and number of NFV nodes on bandwidth consumption when deploying these minimum number of SC instances.

cs.NI↗

arXiv2017

From Query-By-Keyword to Query-By-Example: LinkedIn Talent Search Approach

One key challenge in talent search is to translate complex criteria of a hiring position into a search query, while it is relatively easy for a searcher to list examples of suitable candidates for a given position. To improve search efficiency, we propose the next generation of talent search at LinkedIn, also referred to as Search By Ideal Candidates. In this system, a searcher provides one or several ideal candidates as the input to hire for a given position. The system then generates a query based on the ideal candidates and uses it to retrieve and rank results. Shifting from the traditional Query-By-Keyword to this new Query-By-Example system poses a number of challenges: How to generate a query that best describes the candidates? When moving to a completely different paradigm, how does one leverage previous product logs to learn ranking models and/or evaluate the new system with no existing usage logs? Finally, given the different nature between the two search paradigms, the ranking features typically used for Query-By-Keyword systems might not be optimal for Query-By-Example. This paper describes our approach to solving these challenges. We present experimental results confirming the effectiveness of the proposed solution, particularly on query building and search ranking tasks. As of writing this paper, the new system has been available to all LinkedIn members.

cs.IR↗

arXiv2017

Evolutionary Multitasking for Single-objective Continuous Optimization: Benchmark Problems, Performance Metric, and Baseline Results

In this report, we suggest nine test problems for multi-task single-objective optimization (MTSOO), each of which consists of two single-objective optimization tasks that need to be solved simultaneously. The relationship between tasks varies between different test problems, which would be helpful to have a comprehensive evaluation of the MFO algorithms. It is expected that the proposed test problems will germinate progress the field of the MTSOO research.

cs.NE↗

arXiv2017

Evolutionary Multitasking for Multiobjective Continuous Optimization: Benchmark Problems, Performance Metrics and Baseline Results

In this report, we suggest nine test problems for multi-task multi-objective optimization (MTMOO), each of which consists of two multiobjective optimization tasks that need to be solved simultaneously. The relationship between tasks varies between different test problems, which would be helpful to have a comprehensive evaluation of the MO-MFO algorithms. It is expected that the proposed test problems will germinate progress the field of the MTMOO research.

cs.NE↗

arXiv2017

Adapting Low-Cost Platforms for Robotics Research

Validation of robotics theory on real-world hardware platforms is important to prove the practical feasibility of algorithms. This paper discusses some of the lessons learned while adapting the EvoBot, a low-cost robotics platform that we designed and prototyped, for research in diverse areas in robotics. The EvoBot platform was designed to be a low cost, open source, general purpose robotics platform intended to enable testing and validation of algorithms from a wide variety of sub-fields of robotics. Throughout the paper, we outline and discuss some common failures, practical limitations and inconsistencies between theory and practice that one may encounter while adapting such low-cost platforms for robotics research. We demonstrate these aspects through four representative common robotics tasks- localization, real-time control, swarm consensus and path planning applications, performed using the EvoBots. We also propose some potential solutions to the encountered problems and try to generalize them.

cs.RO↗

arXiv2017

VehSense: Slippery Road Detection Using Smartphones

This paper investigates a new application of vehicular sensing: detecting and reporting the slippery road conditions. We describe a system and associated algorithm to monitor vehicle skidding events using smartphones and OBD-II (On board Diagnostics) adaptors. This system, which we call the VehSense, gathers data from smartphone inertial sensors and vehicle wheel speed sensors, and processes the data to monitor slippery road conditions in real-time. Specifically, two speed readings are collected: 1) ground speed, which is estimated by vehicle acceleration and rotation, and 2) wheel speed, which is retrieved from the OBD-II interface. The mismatch between these two speeds is used to infer a skidding event. Without tapping into vehicle manufactures' proprietary data (e.g., antilock braking system), VehSense is compatible with most of the passenger vehicles, and thus can be easily deployed. We evaluate our system on snow-covered roads at Buffalo, and show that it can detect vehicle skidding effectively.

eess.SY↗

arXiv2017

Service Chain (SC) Mapping with Multiple SC Instances in a Wide Area Network

Network Function Virtualization (NFV) aims to simplify deployment of network services by running Virtual Network Functions (VNFs) on commercial off-the-shelf servers. Service deployment involves placement of VNFs and in-sequence routing of traffic flows through VNFs comprising a Service Chain (SC). The joint VNF placement and traffic routing is usually referred as SC mapping. In a Wide Area Network (WAN), a situation may arise where several traffic flows, generated by many distributed node pairs, require the same SC, one single instance (or occurrence) of that SC might not be enough. SC mapping with multiple SC instances for the same SC turns out to be a very complex problem, since the sequential traversal of VNFs has to be maintained while accounting for traffic flows in various directions. Our study is the first to deal with SC mapping with multiple SC instances to minimize network resource consumption. Exact mathematical modeling of this problem results in a quadratic formulation. We propose a two-phase column-generation-based model and solution in order to get results over large network topologies within reasonable computational times. Using such an approach, we observe that an appropriate choice of only a small set of SC instances can lead to solution very close to the minimum bandwidth consumption.

cs.NI↗

arXiv2017

Learning Dexterous Manipulation for a Soft Robotic Hand from Human Demonstration

Dexterous multi-fingered hands can accomplish fine manipulation behaviors that are infeasible with simple robotic grippers. However, sophisticated multi-fingered hands are often expensive and fragile. Low-cost soft hands offer an appealing alternative to more conventional devices, but present considerable challenges in sensing and actuation, making them difficult to apply to more complex manipulation tasks. In this paper, we describe an approach to learning from demonstration that can be used to train soft robotic hands to perform dexterous manipulation tasks. Our method uses object-centric demonstrations, where a human demonstrates the desired motion of manipulated objects with their own hands, and the robot autonomously learns to imitate these demonstrations using reinforcement learning. We propose a novel algorithm that allows us to blend and select a subset of the most feasible demonstrations to learn to imitate on the hardware, which we use with an extension of the guided policy search framework to use multiple demonstrations to learn generalizable neural network policies. We demonstrate our approach on the RBO Hand 2, with learned motor skills for turning a valve, manipulating an abacus, and grasping.

cs.LG↗

arXiv2017

Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning

People can learn a wide range of tasks from their own experience, but can also learn from observing other creatures. This can accelerate acquisition of new skills even when the observed agent differs substantially from the learning agent in terms of morphology. In this paper, we examine how reinforcement learning algorithms can transfer knowledge between morphologically different agents (e.g., different robots). We introduce a problem formulation where two agents are tasked with learning multiple skills by sharing information. Our method uses the skills that were learned by both agents to train invariant feature spaces that can then be used to transfer other skills from one agent to another. The process of learning these invariant feature spaces can be viewed as a kind of "analogy making", or implicit learning of partial correspondences between two distinct domains. We evaluate our transfer learning algorithm in two simulated robotic manipulation skills, and illustrate that we can transfer knowledge between simulated robotic arms with different numbers of links, as well as simulated arms with different actuation mechanisms, where one robot is torque-driven while the other is tendon-driven.

cs.AI↗

arXiv2016

Learning Dexterous Manipulation Policies from Experience and Imitation

We explore learning-based approaches for feedback control of a dexterous five-finger hand performing non-prehensile manipulation. First, we learn local controllers that are able to perform the task starting at a predefined initial state. These controllers are constructed using trajectory optimization with respect to locally-linear time-varying models learned directly from sensor data. In some cases, we initialize the optimizer with human demonstrations collected via teleoperation in a virtual environment. We demonstrate that such controllers can perform the task robustly, both in simulation and on the physical platform, for a limited range of initial conditions around the trained starting state. We then consider two interpolation methods for generalizing to a wider range of initial conditions: deep learning, and nearest neighbors. We find that nearest neighbors achieve higher performance. Nevertheless, the neural network has its advantages: it uses only tactile and proprioceptive feedback but no visual feedback about the object (i.e. it performs the task blind) and learns a time-invariant policy. In contrast, the nearest neighbors method switches between time-varying local controllers based on the proximity of initial object states sensed via motion capture. While both generalization methods leave room for improvement, our work shows that (i) local trajectory-based controllers for complex non-prehensile manipulation tasks can be constructed from surprisingly small amounts of training data, and (ii) collections of such controllers can be interpolated to form more global controllers. Results are summarized in the supplementary video: https://youtu.be/E0wmO6deqjo

cs.LG↗