Research map / Reinforcement learning / Visual and representation RL
MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research
Mikayel Samvelyan, Robert Kirk, Vitaly Kurin, Jack Parker-Holder, Minqi Jiang, Eric Hambro, Fabio Petroni, Heinrich Kuttler, Edward Grefenstette, Tim Rocktäschel
Read the paperCheck your idea against 137,217 papers
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 monsters, locked doors, or lava tiles to the two-room MultiRoom task | MultiRoom-N2 · MultiRoom-N2 | learning progress | Hurt |
| Add monsters, locked doors, and lava tiles together | MultiRoom-N2 · MultiRoom-N2-Extreme | learning progress | Hurt |
| Increase KeyRoom size from S5 to S15 | KeyRoom · KeyRoom-Random-S15 | reward | Hurt |
| Add moving monsters and deadly lava | River · River | reward | Hurt |
| Require discovering sequences of entity-action relations amid randomization and distracting entities | MiniHack skill acquisition tasks · WoD-Medium and LavaCross | reward | Hurt |
| Train the protagonist with a PAIRED-generated curriculum | PAIRED · MultiRoom-N2-Extreme zero-shot transfer | zero-shot performance | Improved |
| Use a small rather than medium or large agent architecture | IMPALA · Corridor-3 | mean episode return | Improved |
| Use a small rather than medium or large agent architecture | IMPALA · Room-Ultimate-15 and CorridorBattle | mean episode return | Hurt |
Closest papers by meaning
- NAVIX: Scaling MiniGrid Environments with JAX (NeurIPS 2025 · similarity 0.89)
- SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores (ICLR 2024 · similarity 0.89)
- Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning (ICML 2024 · similarity 0.88)
- Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback (ICLR 2024 · similarity 0.88)
- Random Latent Exploration for Deep Reinforcement Learning (ICML 2024 · similarity 0.87)
- Towards General-Purpose Model-Free Reinforcement Learning (ICLR 2025 · similarity 0.87)
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.
