paper-with-me

Papers

Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks

2023-06-24 · NeurIPS 2023 11 · Maxime Chevalier-Boisvert, Bolun Dai, Mark Towers, Rodrigo de Lazcano, Lucas Willems, Salem Lahlou, Suman Pal, Pablo Samuel Castro, Jordan Terry

We present the Minigrid and Miniworld libraries which provide a suite of goal-oriented 2D and 3D environments. The libraries were explicitly created with a minimalistic design paradigm to allow users to rapidly develop new environments for a wide range of research-specific needs. As a result, both have received widescale adoption by the RL community, facilitating research in a wide range of areas. In this paper, we outline the design philosophy, environment details, and their world generation API. We also showcase the additional capabilities brought by the unified API between Minigrid and Miniworld through case studies on transfer learning (for both RL agents and humans) between the different observation spaces. The source code of Minigrid and Miniworld can be found at https://github.com/Farama-Foundation/{Minigrid, Miniworld} along with their documentation at https://{minigrid, miniworld}.farama.org/.

📄 PDF Abstract BibTeX arXiv:2306.13831

Code (2)

farama-foundation/minigrid 공식 구현 pytorch
farama-foundation/miniworld 공식 구현

Tasks

PhilosophyTransfer Learning

Similar Papers 제목 키워드 기반

XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX

2023-12-19 · Alexander Nikulin, Vladislav Kurenkov, Ilya Zisman, Artem Agarkov 외

Inspired by the diversity and depth of XLand and the simplicity and minimalism of MiniGrid, we present XLand-MiniGrid, a suite of tools and grid-world environments for meta-reinforcement learning research. Written in JAX…

DiversityGPUMeta-LearningMeta Reinforcement Learning+2

Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments

2021-01-20 · ICLR 2021 1 · Daochen Zha, Wenye Ma, Lei Yuan, Xia Hu 외

Exploration under sparse reward is a long-standing challenge of model-free reinforcement learning. The state-of-the-art methods address this challenge by introducing intrinsic rewards to encourage exploration in novel st…

MuJoCo

Learning Successor Features the Simple Way

2024-10-29 · Raymond Chua, Arna Ghosh, Christos Kaplanis, Blake A. Richards 외

In Deep Reinforcement Learning (RL), it is a challenge to learn representations that do not exhibit catastrophic forgetting or interference in non-stationary environments. Successor Features (SFs) offer a potential solut…

Continual LearningDeep Reinforcement LearningMuJoCoReinforcement Learning (RL)

skrl: Modular and Flexible Library for Reinforcement Learning

2022-02-08 · Antonio Serrano-Muñoz, Dimitris Chrysostomou, Simon Bøgh, Nestor Arana-Arexolaleiba

skrl is an open-source modular library for reinforcement learning written in Python and designed with a focus on readability, simplicity, and transparency of algorithm implementations. In addition to supporting environme…

Isaac Gym PreviewOmniverse Isaac GymOpenAI GymReinforcement Learning+1

Assessing Policy, Loss and Planning Combinations in Reinforcement Learning using a New Modular Architecture

2022-01-08 · Tiago Gaspar Oliveira, Arlindo L. Oliveira

The model-based reinforcement learning paradigm, which uses planning algorithms and neural network models, has recently achieved unprecedented results in diverse applications, leading to what is now known as deep reinfor…

Deep Reinforcement LearningModel-based Reinforcement Learningreinforcement-learningReinforcement Learning+1