Jelly Bean World: A Testbed for Never-Ending Learning

• URL: http://arxiv.org/abs/2002.06306v1
• Date: Sat, 15 Feb 2020 02:43:16 GMT
• Title: Jelly Bean World: A Testbed for Never-Ending Learning
• Authors: Emmanouil Antonios Platanios and Abulhair Saparov and Tom Mitchell
• Abstract summary: Never-ending learning is a machine learning paradigm that aims to bridge the gap between machine learning and human learning. The Jelly Bean World testbed allows experimentation over two-dimensional grid worlds filled with items and in which agents can navigate. It does so by producing non-stationary environments and facilitating experimentation with multi-task, multi-agent, multi-modal, and curriculum learning settings.
• Score: 9.560980936110234
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Machine learning has shown growing success in recent years. However, current machine learning systems are highly specialized, trained for particular problems or domains, and typically on a single narrow dataset. Human learning, on the other hand, is highly general and adaptable. Never-ending learning is a machine learning paradigm that aims to bridge this gap, with the goal of encouraging researchers to design machine learning systems that can learn to perform a wider variety of inter-related tasks in more complex environments. To date, there is no environment or testbed to facilitate the development and evaluation of never-ending learning systems. To this end, we propose the Jelly Bean World testbed. The Jelly Bean World allows experimentation over two-dimensional grid worlds which are filled with items and in which agents can navigate. This testbed provides environments that are sufficiently complex and where more generally intelligent algorithms ought to perform better than current state-of-the-art reinforcement learning approaches. It does so by producing non-stationary environments and facilitating experimentation with multi-task, multi-agent, multi-modal, and curriculum learning settings. We hope that this new freely-available software will prompt new research and interest in the development and evaluation of never-ending learning systems and more broadly, general intelligence systems.

Related papers

• Open-world Machine Learning: A Review and New Outlooks [83.6401132743407]
  This paper aims to provide a comprehensive introduction to the emerging open-world machine learning paradigm. It aims to help researchers build more powerful AI systems in their respective fields, and to promote the development of artificial general intelligence.
  arXiv  Detail & Related papers  (2024-03-04T06:25:26Z)
• Unsupervised Learning in Complex Systems [0.0]
  This thesis explores the use of complex systems to study learning and adaptation in natural and artificial systems. The goal is to develop autonomous systems that can learn without supervision, develop on their own, and become increasingly complex over time.
  arXiv  Detail & Related papers  (2023-07-11T19:48:42Z)
• General Intelligence Requires Rethinking Exploration [24.980249597326985]
  We argue that exploration is essential to all learning systems, including supervised learning. Generalized exploration serves as a necessary objective for maintaining open-ended learning processes.
  arXiv  Detail & Related papers  (2022-11-15T00:46:15Z)
• Open Environment Machine Learning [84.90891046882213]
  Conventional machine learning studies assume close world scenarios where important factors of the learning process hold invariant. This article briefly introduces some advances in this line of research, focusing on techniques concerning emerging new classes, decremental/incremental features, changing data distributions, varied learning objectives, and discusses some theoretical issues.
  arXiv  Detail & Related papers  (2022-06-01T11:57:56Z)
• Flashlight: Enabling Innovation in Tools for Machine Learning [50.63188263773778]
  We introduce Flashlight, an open-source library built to spur innovation in machine learning tools and systems. We see Flashlight as a tool enabling research that can benefit widely used libraries downstream and bring machine learning and systems researchers closer together.
  arXiv  Detail & Related papers  (2022-01-29T01:03:29Z)
• Collective Intelligence for Deep Learning: A Survey of Recent Developments [11.247894240593691]
  We will provide a historical context of neural network research's involvement with complex systems. We will highlight several active areas in modern deep learning research that incorporate the principles of collective intelligence.
  arXiv  Detail & Related papers  (2021-11-29T08:39:32Z)
• Ten Quick Tips for Deep Learning in Biology [116.78436313026478]
  Machine learning is concerned with the development and applications of algorithms that can recognize patterns in data and use them for predictive modeling. Deep learning has become its own subfield of machine learning. In the context of biological research, deep learning has been increasingly used to derive novel insights from high-dimensional biological data.
  arXiv  Detail & Related papers  (2021-05-29T21:02:44Z)
• Open-world Machine Learning: Applications, Challenges, and Opportunities [0.7734726150561086]
  Open-world machine learning deals with arbitrary inputs (data with unseen classes) to machine learning systems. Traditional machine learning is static learning which is not appropriate for an active environment. This paper presents a systematic review of various techniques for open-world machine learning.
  arXiv  Detail & Related papers  (2021-05-27T21:05:10Z)
• MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale [103.7609761511652]
  We show how a large-scale collective robotic learning system can acquire a repertoire of behaviors simultaneously. New tasks can be continuously instantiated from previously learned tasks. We train and evaluate our system on a set of 12 real-world tasks with data collected from 7 robots.
  arXiv  Detail & Related papers  (2021-04-16T16:38:02Z)
• The Ingredients of Real-World Robotic Reinforcement Learning [71.92831985295163]
  We discuss the elements that are needed for a robotic learning system that can continually and autonomously improve with data collected in the real world. We propose a particular instantiation of such a system, using dexterous manipulation as our case study. We demonstrate that our complete system can learn without any human intervention, acquiring a variety of vision-based skills with a real-world three-fingered hand.
  arXiv  Detail & Related papers  (2020-04-27T03:36:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.