MiniGrid
A lightweight, open-source grid-world reinforcement learning training environment offering minimalistic and configurable tasks. It is widely used for rapid prototyping of reinforcement learning algorithms and agent research.
Timeline (last 90 days)
Empirical testing used 45,000 held-out variable-state histories and 9,000 episodes, covering three external MiniGrid memory environments with a noisy reporting interface introduced.
In MiniGrid, the new certificates accepted 9/9 improvements over the constant incumbent policy and 4/9 improvements over the last-write-wins policy, whereas the previous certificates accepted none.
MiniGrid is a lightweight grid-world environment library widely used in the reinforcement learning community, known for its partial observability scenarios.
NetHack Learning Environment, MiniGrid, and Procgen are well-known reinforcement learning research environments.
Farama基金会同时维护PettingZoo（多智能体环境）、MiniGrid（网格世界环境）、Minari（离线RL数据集标准）等项目
Farama基金会同时维护PettingZoo（多智能体环境）、MiniGrid（网格世界环境）等强化学习相关项目
All Facts (6)
Empirical testing used 45,000 held-out variable-state histories and 9,000 episodes, covering three external MiniGrid memory environments with a noisy reporting interface introduced.
50%UnverifiedIn MiniGrid, the new certificates accepted 9/9 improvements over the constant incumbent policy and 4/9 improvements over the last-write-wins policy, whereas the previous certificates accepted none.
50%UnverifiedMiniGrid is a lightweight grid-world environment library widely used in the reinforcement learning community, known for its partial observability scenarios.
50%UnverifiedNetHack Learning Environment, MiniGrid, and Procgen are well-known reinforcement learning research environments.
50%UnverifiedFarama基金会同时维护PettingZoo（多智能体环境）、MiniGrid（网格世界环境）、Minari（离线RL数据集标准）等项目
50%UnverifiedFarama基金会同时维护PettingZoo（多智能体环境）、MiniGrid（网格世界环境）等强化学习相关项目
50%