SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulation

TL;DR

SoftGym introduces a comprehensive set of simulated benchmarks for deformable object manipulation, enabling reproducible research and evaluation of reinforcement learning algorithms in complex, high-dimensional, and partially observable environments.

Contribution

The paper presents SoftGym, an open-source benchmark suite for deformable object manipulation with standardized API, facilitating research and comparison in this challenging area.

Findings

Existing algorithms struggle with high-dimensional, partially observable states.

SoftGym reveals limitations of current methods in deformable object tasks.

Benchmarking highlights key challenges and directions for future research.

Abstract

Manipulating deformable objects has long been a challenge in robotics due to its high dimensional state representation and complex dynamics. Recent success in deep reinforcement learning provides a promising direction for learning to manipulate deformable objects with data driven methods. However, existing reinforcement learning benchmarks only cover tasks with direct state observability and simple low-dimensional dynamics or with relatively simple image-based environments, such as those with rigid objects. In this paper, we present SoftGym, a set of open-source simulated benchmarks for manipulating deformable objects, with a standard OpenAI Gym API and a Python interface for creating new environments. Our benchmark will enable reproducible research in this important area. Further, we evaluate a variety of algorithms on these tasks and highlight challenges for reinforcement learning algorithms, including dealing with a state representation that has a high intrinsic dimensionality and is partially observable. The experiments and analysis indicate the strengths and limitations of existing methods in the context of deformable object manipulation that can help point the way forward for future methods development. Code and videos of the learned policies can be found on our project website.