Jelly Bean World: A Testbed for Never-Ending Learning

By Emmanouil Antonios Platanios, Abulhair Saparov, Tom Michael Mitchell. 2020

27 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Management Science and Operations Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Management Science and Operations Research

Citations in the corpus

Continual World: A Robotic Benchmark For Continual Reinforcement Learning (2021, background): “Jelly Bean World [37] provide interesting procedurally”
Continuous Coordination As a Realistic Scenario for Lifelong Learning (2021, background): “Jelly Bean World (JBW) (Platanios et al., 2020) is a testbed introduced to develop agents with never-ending learning capabilities.”
Towards Continual Reinforcement Learning: A Review and Perspectives (2020, background): “In particular, Jelly Bean World supports a variety of nonstationary environment configurations including multi-task, multi-agent, multi-modal, and curriculum learning settings.”
Reactive Exploration to Cope with Non-Stationarity in Lifelong Reinforcement Learning (2022, methodology): “Environments in JBW are procedurally generated POMDPs, where only a fraction of the created world is visible to the agent.”
CORA: Benchmarks, Baselines, and Metrics as a Platform for Continual Reinforcement Learning Agents (2021, background): “Procgen (Cobbe et al., 2020) and MiniHack (Küttler et al., 2020; Samvelyan et al., 2021), two of our other benchmarks, are procedurally-generated, like Jelly Bean World (Platanios et al., 2020) which is a procedurally-generated 2D gridworld proposed as a testbed for continual learning agents.”