Task (computing)

About: Task (computing) is a research topic. Over the lifetime, 9718 publications have been published within this topic receiving 129364 citations.

Learning modular neural network policies for multi-task and multi-robot transfer

Abstract: Reinforcement learning (RL) can automate a wide variety of robotic skills, but learning each new skill requires considerable real-world data collection and manual representation engineering to design policy classes or features. Using deep reinforcement learning to train general purpose neural network policies alleviates some of the burden of manual representation engineering by using expressive policy classes, but exacerbates the challenge of data collection, since such methods tend to be less efficient than RL with low-dimensional, hand-designed representations. Transfer learning can mitigate this problem by enabling us to transfer information from one skill to another and even from one robot to another. We show that neural network policies can be decomposed into “task-specific” and “robot-specific” modules, where the task-specific modules are shared across robots, and the robot-specific modules are shared across all tasks on that robot. This allows for sharing task information, such as perception, between robots and sharing robot information, such as dynamics and kinematics, between tasks. We exploit this decomposition to train mix-and-match modules that can solve new robot-task combinations that were not seen during training. Using a novel approach to train modular neural networks, we demonstrate the effectiveness of our transfer method for enabling zero-shot generalization with a variety of robots and tasks in simulation for both visual and non-visual tasks.

Curriculum learning of multiple tasks

Abstract: Sharing information between multiple tasks enables algorithms to achieve good generalization performance even from small amounts of training data. However, in a realistic scenario of multi-task learning not all tasks are equally related to each other, hence it could be advantageous to transfer information only between the most related tasks. In this work we propose an approach that processes multiple tasks in a sequence with sharing between subsequent tasks instead of solving all tasks jointly. Subsequently, we address the question of curriculum learning of tasks, i.e. finding the best order of tasks to be learned. Our approach is based on a generalization bound criterion for choosing the task order that optimizes the average expected classification performance over all tasks. Our experimental results show that learning multiple related tasks sequentially can be more effective than learning them jointly, the order in which tasks are being solved affects the overall performance, and that our model is able to automatically discover a favourable order of tasks.

Alpaca: intermittent execution without checkpoints

Abstract: The emergence of energy harvesting devices creates the potential for batteryless sensing and computing devices. Such devices operate only intermittently, as energy is available, presenting a number of challenges for software developers. Programmers face a complex design space requiring reasoning about energy, memory consistency, and forward progress. This paper introduces Alpaca, a low-overhead programming model for intermittent computing on energy-harvesting devices. Alpaca programs are composed of a sequence of user-defined tasks. The Alpaca runtime preserves execution progress at the granularity of a task. The key insight in Alpaca is the privatization of data shared between tasks. Shared values written in a task are detected using idempotence analysis and copied into a buffer private to the task. At the end of the task, modified values from the private buffer are atomically committed to main memory, ensuring that data remain consistent despite power failures. Alpaca provides a familiar programming interface, a highly efficient runtime model, and places fewer restrictions on a target device's hardware architecture. We implemented a prototype of Alpaca as an extension to C with an LLVM compiler pass. We evaluated Alpaca, and directly compared to two systems from prior work. Alpaca eliminates checkpoints, which improves performance up to 15x, and avoids static multi-versioning, which improves memory consumption by up to 5.5x.

Task scheduler for a miltiprocessor system

Abstract: A task scheduler for use in a multiprocessor, multitasking system in which a plurality of processor complexes, each containing one or more processors, concurrently execute tasks into which jobs such as database queries are divided. A desired level of concurrent task activity, such as the maximum number of tasks that can be executed concurrently without queuing of tasks, is defined for each processor complex. Each job is assigned a weight in accordance with the external priority accorded to the job. For each job there is defined a desired level of concurrent; task activity that is proportional to its share of the total weight assigned to all concurrently executing jobs. The jobs are prioritized for execution of awaiting tasks in accordance with the discrepancy between the desired level of multitasking activity and the actual level of multitasking activity for each job. Awaiting tasks are preferentially scheduled from jobs with the largest discrepancy between the desired and actual levels of concurrent task activity and are preferentially assigned to the processor complexes with the largest discrepancy between the desired and actual levels of concurrent task activity. The scheduler attempts to assign each task to a processor for which the task has an affinity or at least neutrality in terms of relative execution speed.

A distributed tasks allocation scheme in multi-UAV context

Abstract: This paper deals with the task allocation problem in multi-robot systems. We propose a completely distributed architecture, where robots dynamically allocate their tasks while they are building their plans. We first focus on the problem of simple "goto" tasks allocation: our approach involves an incremental task allocation algorithm based on the Contract-Net protocol. We introduce a parameter called equity coefficient in order to equilibrate the workload between the different robots and to control the triggering of the auction process. Then, we address the problem raised by temporal constraints between tasks by dynamically specifying temporary hierarchies among the tasks. Tests run in simulation quantify the benefits of our improvements.