Flatland: a Lightweight First-Person 2-D Environment for Reinforcement Learning

2018-09-03 · Hugo Caselles-Dupré, Louis Annabi, Oksana Hagen, Michael Garcia-Ortiz, David Filliat

Flatland is a simple, lightweight environment for fast prototyping and testing of reinforcement learning agents. It is of lower complexity compared to similar 3D platforms (e.g. DeepMind Lab or VizDoom), but emulates physical properties of the real world, such as continuity, multi-modal partially-observable states with first-person view and coherent physics. We propose to use it as an intermediary benchmark for problems related to Lifelong Learning. Flatland is highly customizable and offers a wide range of task difficulty to extensively evaluate the properties of artificial agents. We experiment with three reinforcement learning baseline agents and show that they can rapidly solve a navigation task in Flatland. A video of an agent acting in Flatland is available here: https://youtu.be/I5y6Y2ZypdA.

📄 PDF Abstract BibTeX arXiv:1809.00510

Code (0)

등록된 구현이 없습니다.

Tasks

Lifelong learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Flatland-RL : Multi-Agent Reinforcement Learning on Trains

2020-12-10 · Sharada Mohanty, Erik Nygren, Florian Laurent, Manuel Schneider 외

Efficient automated scheduling of trains remains a major challenge for modern railway systems. The underlying vehicle rescheduling problem (VRSP) has been a major focus of Operations Research (OR) since decades. Traditio…

Imitation Learning Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning+2

FlatLand: Personalized Graph Federated Learning via Tailored Lorentz Space

2026-08-21 · Jiahong Liu, Ram Samarth B B, Xinyu Fu, Menglin Yang 외 arxiv

Federated learning enables privacy-preserving collaborative training, but highly heterogeneous client data remain challenging, especially in graph federated learning where clients possess structurally diverse graphs. Exi…

Personalized Federated Learning Graph Learning

Flatland Competition 2020: MAPF and MARL for Efficient Train Coordination on a Grid World

2021-03-30 · Florian Laurent, Manuel Schneider, Christian Scheller, Jeremy Watson 외

The Flatland competition aimed at finding novel approaches to solve the vehicle re-scheduling problem (VRSP). The VRSP is concerned with scheduling trips in traffic networks and the re-scheduling of vehicles when disrupt…

Multi-agent Reinforcement Learning Scheduling

3DoF Localization from a Single Image and an Object Map: the Flatlandia Problem and Dataset

2023-04-13 · Matteo Toso, Matteo Taiana, Stuart James, Alessio Del Bue

Efficient visual localization is crucial to many applications, such as large-scale deployment of autonomous agents and augmented reality. Traditional visual localization, while achieving remarkable accuracy, relies on ex…

Privacy Preserving Visual Localization

ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning

2016-05-06 · Michał Kempka, Marek Wydmuch, Grzegorz Runc, Jakub Toczek 외

The recent advances in deep neural networks have led to effective vision-based reinforcement learning methods that have been employed to obtain human-level controllers in Atari 2600 games from pixel data. Atari 2600 game…

Atari Games FPS Games Game of Doom Q-Learning+3