RECORD
Gym-Ignition: Reproducible Robotic Simulations for Reinforcement Learning
Robotics · Submitted 5 Nov 2019
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim This paper presents Gym-Ignition, a new framework to create reproducible robotic environments for reinforcement learning research.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
This paper presents Gym-Ignition, a new framework to create reproducible robotic environments for reinforcement learning research. It interfaces with the new generation of Gazebo, part of the Ignition Robotics suite, which provides three main improvements for reinforcement learning applications compared to the alternatives: 1) the modular architecture enables using the simulator as a C++ library, simplifying the interconnection with external software; 2) multiple physics and rendering engines are supported as plugins, simplifying their selection during the execution; 3) the new distributed simulation capability allows simulating complex scenarios while sharing the load on multiple workers and machines. The core of Gym-Ignition is a component that contains the Ignition Gazebo simulator and exposes a simple interface for its configuration and execution. We provide a Python package that allows developers to create robotic environments simulated in Ignition Gazebo. Environments expose the common OpenAI Gym interface, making them compatible out-of-the-box with third-party frameworks containing reinforcement learning algorithms. Simulations can be executed in both headless and GUI mode, the physics engine can run in accelerated mode, and instances can be parallelized. Furthermore, the Gym-Ignition software architecture provides abstraction of the Robot and the Task, making environments agnostic on the specific runtime. This abstraction allows their execution also in a real-time setting on actual robotic platforms, even if driven by different middlewares.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | This paper presents Gym-Ignition, a new framework to create reproducible robotic environments for reinforcement learning research. | contribution 1.00 | 0.86 | 0.27 | asserted 1.00 |
| s1 | It interfaces with the new generation of Gazebo, part of the Ignition Robotics suite, which provides three main improvements for reinforcement learning applications compared to the alternatives: 1) the modular architecture enables using the simulator as a C++ library, simplifying the interconnection with external software; 2) multiple physics and rendering engines are supported as plugins, simplifying their selection during the execution; 3) the new distributed simulation capability allows simulating complex scenarios while sharing the load on multiple workers and machines. | method 0.51 | 0.16 | 0.07 | asserted 1.00 |
| s2 | The core of Gym-Ignition is a component that contains the Ignition Gazebo simulator and exposes a simple interface for its configuration and execution. | method 0.70 | 0.72 | 0.06 | asserted 1.00 |
| s3 | We provide a Python package that allows developers to create robotic environments simulated in Ignition Gazebo. | contribution 0.83 | 0.90 | 0.04 | asserted 1.00 |
| s4 | Environments expose the common OpenAI Gym interface, making them compatible out-of-the-box with third-party frameworks containing reinforcement learning algorithms. | contribution 0.66 | 0.67 | 0.06 | asserted 1.00 |
| s5 | Simulations can be executed in both headless and GUI mode, the physics engine can run in accelerated mode, and instances can be parallelized. | method 0.61 | 0.57 | 0.03 | asserted 0.80 |
| s6 | Furthermore, the Gym-Ignition software architecture provides abstraction of the Robot and the Task, making environments agnostic on the specific runtime. | method 0.56 | 0.80 | 0.06 | asserted 1.00 |
| s7 | This abstraction allows their execution also in a real-time setting on actual robotic platforms, even if driven by different middlewares. | contribution 0.60 | 0.51 | 0.08 | asserted 0.62 |
What was examined, and what was not
- arXiv listing abstract v2
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
This paper presents Gym-Ignition, a new framework to create reproducible robotic environments for reinforcement learning research. It interfaces with the new generation of Gazebo, part of the Ignition Robotics suite, which provides three main improvements for reinforcement learning applications compared to the alternatives: 1) the modular architecture enables using the simulator as a C++ library, simplifying the interconnection with external software; 2) multiple physics and rendering engines are supported as plugins, simplifying their selection during the execution; 3) the new distributed simulation capability allows simulating complex scenarios while sharing the load on multiple workers and machines. The core of Gym-Ignition is a component that contains the Ignition Gazebo simulator and exposes a simple interface for its configuration and execution. We provide a Python package that allows developers to create robotic environments simulated in Ignition Gazebo. Environments expose the common OpenAI Gym interface, making them compatible out-of-the-box with third-party frameworks containing reinforcement learning algorithms. Simulations can be executed in both headless and GUI mode, the physics engine can run in accelerated mode, and instances can be parallelized. Furthermore, the Gym-Ignition software architecture provides abstraction of the Robot and the Task, making environments agnostic on the specific runtime. This abstraction allows their execution also in a real-time setting on actual robotic platforms, even if driven by different middlewares.
Human review
How the literature uses it
What this paper does with the arXiv papers it cites
What it cites · 7 sentences without a confident label
Uses the method or tool of 1 paper
-
For both domains, we provide the support of exposing the common OpenAI Gym interface [ref] .
OpenAI Gym · Introduction · 0.87
Cites as background 7 papers
-
The process of training a policy in simulation and then transferring it to the real world is better known as sim-to-real [ref] , and the difference between simulation and reality is typically addressed as reality gap.
Transfer from Simulation to Real World through Learning Deep Inverse Dynamics Model · Introduction · 0.94
-
The process of training a policy in simulation and then transferring it to the real world is better known as sim-to-real [ref] , and the difference between simulation and reality is typically addressed as reality gap.
Assessing Transferability from Simulation to Reality for Reinforcement Learning · Introduction · 0.94
-
Classic techniques in domain randomization [ref] operate on parameters of the physics engine.
BayesSim: adaptive domain randomization via probabilistic inference for robotics simulators · Background · 0.82
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.