Research map / Reinforcement learning / Visual and representation RL
Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks
Maxime Chevalier-Boisvert, Bolun Dai, Mark Towers, Rodrigo De Lazcano Perez-Vicente, Lucas Willems, Salem Lahlou, Suman Pal, Pablo Samuel Castro, J K Terry
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add transferred critic network weights (not frozen) from Minigrid (ablation) | PPO on miniworld-gotoobj-env · Miniworld GoToObj | transfer improvement (%): 3.993 | Improved |
| also transfer actor weights alongside critic and mission (ablation) | PPO on miniworld-gotoobj-env · Miniworld GoToObj | transfer improvement (%): 3.207 -> -9.494 | Hurt |
| freeze transferred weights (critic+mission) (ablation) | PPO on miniworld-gotoobj-env · Miniworld GoToObj | transfer improvement (%): 3.207 -> 0.001 | Hurt |
| freeze transferred critic weights (ablation) | PPO on miniworld-gotoobj-env · Miniworld GoToObj | transfer improvement (%): 3.993 -> 2.760 | Hurt |
| transfer actor weights only (ablation) | PPO on miniworld-gotoobj-env · Miniworld GoToObj | transfer improvement (%): -8.881 | Hurt |
| pre-train humans on Minigrid before Miniworld | human subjects on Miniworld FourRooms · Miniworld FourRooms | mean reward | No clear effect |
Closest papers by meaning
- XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX (NeurIPS 2024 · similarity 0.88)
- NAVIX: Scaling MiniGrid Environments with JAX (NeurIPS 2025 · similarity 0.86)
- PWM: Policy Learning with Multi-Task World Models (ICLR 2025 · similarity 0.84)
- Using Unity to Help Solve Reinforcement Learning (NeurIPS 2024 · similarity 0.84)
- XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning (ICLR 2025 · similarity 0.84)
- RL-GPT: Integrating Reinforcement Learning and Code-as-policy (NeurIPS 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
