VisualEnv: visual Gym environments with Blender

• URL: http://arxiv.org/abs/2111.08096v1
• Date: Mon, 15 Nov 2021 21:43:43 GMT
• Title: VisualEnv: visual Gym environments with Blender
• Authors: Andrea Scorsoglio, Roberto Furfaro
• Abstract summary: VisualEnv is a new tool for creating visual environment for reinforcement learning. It is the product of an integration of open-source modelling and rendering software, Blender, and a python module used to generate environment model for simulation, OpenAI Gym.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: In this paper VisualEnv, a new tool for creating visual environment for reinforcement learning is introduced. It is the product of an integration of an open-source modelling and rendering software, Blender, and a python module used to generate environment model for simulation, OpenAI Gym. VisualEnv allows the user to create custom environments with photorealistic rendering capabilities and full integration with python. The framework is described and tested on a series of example problems that showcase its features for training reinforcement learning agents.

Related papers

• AI4EOSC: a Federated Cloud Platform for Artificial Intelligence in Scientific Research [44.97138432029079]
  We describe a federated compute platform dedicated to support Artificial Intelligence in scientific workloads.<n>It delivers consistent, transparent access to a federation of physically distributed e-Infrastructures.<n>The platform is able to offer an integrated user experience covering the full Machine Learning lifecycle.
  arXiv  Detail & Related papers  (2025-12-18T12:20:31Z)
• PIPer: On-Device Environment Setup via Online Reinforcement Learning [74.52354321028493]
  Automated environment setup methods could assist developers by providing fully configured environments for arbitrary repositories without manual effort.<n>Recent studies reveal that even state-of-the-art Large Language Models (LLMs) achieve limited success in automating this task.<n>We combine supervised fine-tuning for generating correct scripts and Reinforcement Learning with Verifiable Rewards (RLVR) to adapt it to the task of environment setup.<n>On EnvBench-Python, our method enables Qwen3-8B (a model runnable on consumer hardware) to perform on par with larger models-Qwen3-32B and GPT-4
  arXiv  Detail & Related papers  (2025-09-29T20:03:05Z)
• ScreenExplorer: Training a Vision-Language Model for Diverse Exploration in Open GUI World [11.401732438387704]
  Existing GUI agents based on vision-language models (VLMs) often fail to generalize to novel environments.<n>We introduce ScreenExplorer, a VLM trained via Group Relative Policy Optimization (GRPO) in real, dynamic, and open-ended GUI environments.<n>We also introduce a world-model-based curiosity reward function to help the agent overcome the cold-start phase of exploration.
  arXiv  Detail & Related papers  (2025-05-25T11:13:03Z)
• Exploration-Driven Generative Interactive Environments [53.05314852577144]
  We focus on using many virtual environments for inexpensive, automatically collected interaction data. We propose a training framework merely using a random agent in virtual environments. Our agent is fully independent of environment-specific rewards and thus adapts easily to new environments.
  arXiv  Detail & Related papers  (2025-04-03T12:01:41Z)
• Blendify -- Python rendering framework for Blender [31.334130573156937]
  Blendify is a Python-based framework that seamlessly integrates with Blender. It automates object creation, handling the colors and material linking, and implementing features such as shadow-catcher objects.
  arXiv  Detail & Related papers  (2024-10-23T13:29:02Z)
• Flex: End-to-End Text-Instructed Visual Navigation from Foundation Model Features [59.892436892964376]
  We investigate the minimal data requirements and architectural adaptations necessary to achieve robust closed-loop performance with vision-based control policies.<n>Our findings are synthesized in Flex (Fly lexically), a framework that uses pre-trained Vision Language Models (VLMs) as frozen patch-wise feature extractors.<n>We demonstrate the effectiveness of this approach on a quadrotor fly-to-target task, where agents trained via behavior cloning successfully generalize to real-world scenes.
  arXiv  Detail & Related papers  (2024-10-16T19:59:31Z)
• MALPOLON: A Framework for Deep Species Distribution Modeling [3.1457219084519004]
  MALPOLON aims to facilitate training and inferences of deep species distribution models (deep-SDM) It is written in Python and built upon the PyTorch library. The framework is open-sourced on GitHub and PyPi.
  arXiv  Detail & Related papers  (2024-09-26T17:45:10Z)
• pyvene: A Library for Understanding and Improving PyTorch Models via Interventions [79.72930339711478]
  $textbfpyvene$ is an open-source library that supports customizable interventions on a range of different PyTorch modules. We show how $textbfpyvene$ provides a unified framework for performing interventions on neural models and sharing the intervened upon models with others.
  arXiv  Detail & Related papers  (2024-03-12T16:46:54Z)
• gym-saturation: Gymnasium environments for saturation provers (System description) [0.0]
  We contribute usage examples with two different provers: Vampire and iProver. We demonstrate how environment wrappers can transform a prover into a problem similar to a multi-armed bandit.
  arXiv  Detail & Related papers  (2023-09-16T15:25:39Z)
• BU-CVKit: Extendable Computer Vision Framework for Species Independent Tracking and Analysis [7.036239435275302]
  We present a computer vision framework that allows creation of research pipelines with chain Processors. The community can create plugins of their work for the framework, hence improving the reusability, accessibility, and exposure of their work. We show examples of behavioral pipelines created through the sample plugins created for our framework.
  arXiv  Detail & Related papers  (2023-06-07T19:12:03Z)
• CoRL: Environment Creation and Management Focused on System Integration [0.0]
  The Core Reinforcement Learning library (CoRL) is a modular, composable, and hyper-configurable environment creation tool. It allows minute control over agent observations, rewards, and done conditions through the use of easy-to-read configuration files, pydantic validators, and a functor design pattern.
  arXiv  Detail & Related papers  (2023-03-03T19:01:53Z)
• Masked World Models for Visual Control [90.13638482124567]
  We introduce a visual model-based RL framework that decouples visual representation learning and dynamics learning. We demonstrate that our approach achieves state-of-the-art performance on a variety of visual robotic tasks.
  arXiv  Detail & Related papers  (2022-06-28T18:42:27Z)
• VRKitchen2.0-IndoorKit: A Tutorial for Augmented Indoor Scene Building in Omniverse [77.52012928882928]
  INDOORKIT is a built-in toolkit for NVIDIA OMNIVERSE. It provides flexible pipelines for indoor scene building, scene randomizing, and animation controls.
  arXiv  Detail & Related papers  (2022-06-23T17:53:33Z)
• Interactive Visualization of Protein RINs using NetworKit in the Cloud [57.780880387925954]
  In this paper, we consider an example from protein dynamics, specifically residue interaction networks (RINs) We use NetworKit to build a cloud-based environment that enables domain scientists to run their visualization and analysis on large compute servers. To demonstrate the versatility of this approach, we use it to build a custom Jupyter-based widget for RIN visualization.
  arXiv  Detail & Related papers  (2022-03-02T17:41:45Z)
• Evaluating Continual Learning Algorithms by Generating 3D Virtual Environments [66.83839051693695]
  Continual learning refers to the ability of humans and animals to incrementally learn over time in a given environment. We propose to leverage recent advances in 3D virtual environments in order to approach the automatic generation of potentially life-long dynamic scenes with photo-realistic appearance. A novel element of this paper is that scenes are described in a parametric way, thus allowing the user to fully control the visual complexity of the input stream the agent perceives.
  arXiv  Detail & Related papers  (2021-09-16T10:37:21Z)
• DIETERpy: a Python framework for The Dispatch and Investment Evaluation Tool with Endogenous Renewables [62.997667081978825]
  DIETER is an open-source power sector model designed to analyze future settings with very high shares of variable renewable energy sources. It minimizes overall system costs, including fixed and variable costs of various generation, flexibility and sector coupling options. We introduce DIETERpy that builds on the existing model version, written in the General Algebraic Modeling System (GAMS) and enhances it with a Python framework.
  arXiv  Detail & Related papers  (2020-10-02T09:27:33Z)

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.