---
title: "Ghost in the Minecraft — paper by Zhu et al. (2023)"
description: "The authors propose Ghost in the Minecraft (GITM), which replaces direct goal-to-keyboard mapping… 28 references, cited by 71 papers here."
authors: ["Xizhou Zhu", "Yuntao Chen", "Hao Tian", "Chenxin Tao", "Weijie Su", "Chenyu Yang", "Gao Huang", "Bin Li", "Lewei Lu", "Xiaogang Wang", "Yu Qiao", "Zhaoxiang Zhang", "Jifeng Dai"]
year: 2023
venue: "arXiv:2305.17144"
source: "https://arxiv.org/abs/2305.17144"
doi: "10.48550/arxiv.2305.17144"
arxiv: "2305.17144"
licence: "arXiv — non-exclusive license to distribute"
licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/zhu-2023-ghost-minecraft-generally-capable-agents/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhu-2023-ghost-minecraft-generally-capable-agents/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2023](https://md.research.elamur.ai/free/en/papers/2023/page/8/) / Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory

# Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory

**Authors:** [Xizhou Zhu](https://md.research.elamur.ai/free/en/authors/xizhou-zhu/), [Yuntao Chen](https://md.research.elamur.ai/free/en/authors/yuntao-chen/), [Hao Tian](https://md.research.elamur.ai/free/en/authors/hao-tian/), Chenxin Tao, [Weijie Su](https://md.research.elamur.ai/free/en/authors/weijie-su/), Chenyu Yang, [Gao Huang](https://md.research.elamur.ai/free/en/authors/gao-ming-huang/), [Bin Li](https://md.research.elamur.ai/free/en/authors/bin-li/), [Lewei Lu](https://md.research.elamur.ai/free/en/authors/lewei-lu/), Xiaogang Wang, [Yu Qiao](https://md.research.elamur.ai/free/en/authors/yu-qiao/), [Zhaoxiang Zhang](https://md.research.elamur.ai/free/en/authors/zhaoxiang-zhang/) and [Jifeng Dai](https://md.research.elamur.ai/free/en/authors/jifeng-dai/) · **Year:** 2023 · **Venue:** arXiv:2305.17144 · **Licence:** [arXiv — non-exclusive license to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2305.17144) · [PDF](https://arxiv.org/pdf/2305.17144) · [DOI 10.48550/arxiv.2305.17144](https://doi.org/10.48550/arxiv.2305.17144) · [arXiv 2305.17144](https://arxiv.org/abs/2305.17144) · [OpenAlex](https://openalex.org/W4378768661)

**Citations:** 25 citations (OpenAlex, 2026-10-14) · [71](https://md.research.elamur.ai/free/en/papers/zhu-2023-ghost-minecraft-generally-capable-agents/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Earlier Minecraft agents rely mostly on reinforcement learning and target a single objective, ObtainDiamond, which involves under 5% of the game's item types. They reach roughly 20% success there and need enormous numbers of training steps. The authors propose Ghost in the Minecraft (GITM), which replaces direct goal-to-keyboard mapping with a hierarchy of three LLM-driven components:

- **LLM Decomposer:** splits a goal into a sub-goal tree, using knowledge gathered from the web.
- **LLM Planner:** turns each sub-goal into a list of structured actions, using execution feedback. It also stores successful plans in a text-based memory.
- **LLM Interface:** converts those actions into low-level controls.

GITM improves ObtainDiamond success by 47.5 percentage points over prior methods. It is also the first agent to obtain every item in the Minecraft Overworld technology tree. Training needs no GPU, only a single 32-core CPU node. This suggests that LLM planning with explicit knowledge and memory can be a far cheaper and more general alternative to RL for long-horizon tasks.

## Key points
- GITM unlocked all 262 items in the Overworld tech tree. Earlier agents (VPT, DreamerV3, DEPS) reached only 78 items, about 30%.
- **Structured actions:** the action set has 13 entries, including explore, mine, craft, smelt and dig_down. Sub-goals follow an (Object, Count, Material, Tool, Info) format.
- **Diamond success:** on diamonds, GITM is about 3.5× more successful than competing methods.
- **Cost:** it uses over 10,000× fewer environment steps and trains in about 2 days on one CPU node. VPT needs 6,480 GPU days and DreamerV3 needs 17.
- **Ablation:** each setting ran 40 games, with a 12,000-step limit and up to 30 LLM queries per sub-goal. Diamond success rose with each added component:

  | Configuration | Diamond success |
  |---|---|
  | Goal decomposition alone | 0% |
  | + Feedback | 5% |
  | + External knowledge | 35% |
  | + Text-based memory | 67.5% |

  Iron pickaxe success reached 95% with all components.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Tsinghua University](https://md.research.elamur.ai/free/en/universities/tsinghua-university/) — University, Beijing, China · 415 works · 94,028 citations
- [University of Science and Technology of China](https://md.research.elamur.ai/free/en/universities/university-of-science-and-technology-of-china/) — University, Hefei, China · 145 works · 114,409 citations
- [Chinese University of Hong Kong](https://md.research.elamur.ai/free/en/universities/chinese-university-of-hong-kong/) — University, Hong Kong, China · 159 works · 16,154 citations
- [Chinese Academy of Sciences](https://md.research.elamur.ai/free/en/government/chinese-academy-of-sciences/) — Government body, Beijing, China · 246 works · 24,951 citations
- [Shanghai Artificial Intelligence Laboratory](https://md.research.elamur.ai/free/en/labs/shanghai-artificial-intelligence-laboratory/) — Research institute, Shanghai, China · 152 works · 13,166 citations
- [Institute of Automation](https://md.research.elamur.ai/free/en/labs/institute-of-automation/) — Research institute, Beijing, China · 87 works · 14,883 citations
- [Sensetime](https://md.research.elamur.ai/free/en/companies/sensetime/) — Company, Beijing, China · 13 works · 2,161 citations

📚 Shelves (2): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works

## Cite

Cite as: Xizhou Zhu, Yuntao Chen, Hao Tian, Chenxin Tao, Weijie Su, Chenyu Yang, Gao Huang, Bin Li, Lewei Lu, Xiaogang Wang, Yu Qiao, Zhaoxiang Zhang and Jifeng Dai. 2023. Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory. arXiv:2305.17144.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{zhu2023ghost,
  title = {{Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory}},
  author = {Xizhou Zhu, Yuntao Chen, Hao Tian, Chenxin Tao, Weijie Su, Chenyu Yang, Gao Huang, Bin Li, Lewei Lu, Xiaogang Wang, Yu Qiao, Zhaoxiang Zhang and Jifeng Dai},
  year = {2023},
  doi = {10.48550/arxiv.2305.17144},
  eprint = {2305.17144},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2305.17144}
}
```

- [← previous Faithfulness Tests for Natural Language Explanations](https://md.research.elamur.ai/free/en/papers/atanasova-2023-faithfulness-tests-natural-language-explanations/)
- [next → Identifying the Risks of LM Agents with an LM-Emulated Sandbox](https://md.research.elamur.ai/free/en/papers/ruan-2023-identifying-risks-lm-agents-lm/)
- [↑ back to papers of 2023](https://md.research.elamur.ai/free/en/papers/2023/page/8/)

## References

28 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. A. Amiranashvili, N. Dorka, W. Burgard, V. Koltun, and T. Brox. Scaling imitation learning in minecraft. arXiv preprint arXiv:2007.02701, 2020. — [arXiv:2007.02701](https://arxiv.org/abs/2007.02701) [find](https://scholar.google.com/scholar?q=A%2E+Amiranashvili%2C+N%2E+Dorka%2C+W%2E+Burgard%2C+V%2E+Koltun%2C+and+T%2E+Brox%2E+Scaling+imitation+learning+in+minecraft%2E+arXiv+preprint+arXiv%3A2007%2E02701%2C+2020%2E+%E2%80%94+%5BarXiv%3A2007%2E02701%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2007%2E02701%29)
2. B. Baker, I. Akkaya, P. Zhokov, J. Huizinga, J. Tang, A. Ecoffet, B. Houghton, R. Sampedro, and J. Clune. Video pretraining (vpt): Learning to act by watching unlabeled online videos. Advances in Neural Information Processing Systems, 35:24639–24654, 2022. [find](https://scholar.google.com/scholar?q=B%2E+Baker%2C+I%2E+Akkaya%2C+P%2E+Zhokov%2C+J%2E+Huizinga%2C+J%2E+Tang%2C+A%2E+Ecoffet%2C+B%2E+Houghton%2C+R%2E+Sampedro%2C+and+J%2E+Clune%2E+Video+pretraining+%28vpt%29%3A+Learning+to+act+by+watching+unlabeled+online+videos%2E+Advances+in+Neur)
3. S. Cai, Z. Wang, X. Ma, A. Liu, and Y. Liang. Open-world multi-task control through goal-aware representation learning and adaptive horizon prediction. arXiv preprint arXiv:2301.10034, 2023. [find](https://scholar.google.com/scholar?q=S%2E+Cai%2C+Z%2E+Wang%2C+X%2E+Ma%2C+A%2E+Liu%2C+and+Y%2E+Liang%2E+Open%2Dworld+multi%2Dtask+control+through+goal%2Daware+representation+learning+and+adaptive+horizon+prediction%2E+arXiv+preprint+arXiv%3A2301%2E10034%2C+2023%2E)
4. D. Driess, F. Xia, M. S. Sajjadi, C. Lynch, A. Chowdhery, B. Ichter, A. Wahid, J. Tompson, Q. Vuong, T. Yu, et al. Palm-e: An embodied multimodal language model. arXiv preprint arXiv:2303.03378, 2023. [find](https://scholar.google.com/scholar?q=D%2E+Driess%2C+F%2E+Xia%2C+M%2E+S%2E+Sajjadi%2C+C%2E+Lynch%2C+A%2E+Chowdhery%2C+B%2E+Ichter%2C+A%2E+Wahid%2C+J%2E+Tompson%2C+Q%2E+Vuong%2C+T%2E+Yu%2C+et+al%2E+Palm%2De%3A+An+embodied+multimodal+language+model%2E+arXiv+preprint+arXiv%3A2303%2E03378%2C+2023%2E)
5. L. Fan, G. Wang, Y. Jiang, A. Mandlekar, Y. Yang, H. Zhu, A. Tang, D.-A. Huang, Y. Zhu, and A. Anandkumar. [Minedojo: Building open-ended embodied agents with internet-scale knowledge](https://md.research.elamur.ai/free/en/papers/fan-2022-minedojo-building-open-ended-embodied/). arXiv preprint arXiv:2206.08853, 2022.
6. W. H. Guss, S. Milani, N. Topin, B. Houghton, S. Mohanty, A. Melnik, A. Harter, B. Buschmaas, B. Jaster, C. Berganski, et al. Towards robust and domain agnostic reinforcement learning competitions: Minerl 2020. In NeurIPS 2020 Competition and Demonstration Track, pages 233–252. PMLR, 2021. [find](https://scholar.google.com/scholar?q=W%2E+H%2E+Guss%2C+S%2E+Milani%2C+N%2E+Topin%2C+B%2E+Houghton%2C+S%2E+Mohanty%2C+A%2E+Melnik%2C+A%2E+Harter%2C+B%2E+Buschmaas%2C+B%2E+Jaster%2C+C%2E+Berganski%2C+et+al%2E+Towards+robust+and+domain+agnostic+reinforcement+learning+competitions%3A+Mi)
7. D. Hafner, J. Pasukonis, J. Ba, and T. Lillicrap. Mastering diverse domains through world models. arXiv preprint arXiv:2301.04104, 2023. [find](https://scholar.google.com/scholar?q=D%2E+Hafner%2C+J%2E+Pasukonis%2C+J%2E+Ba%2C+and+T%2E+Lillicrap%2E+Mastering+diverse+domains+through+world+models%2E+arXiv+preprint+arXiv%3A2301%2E04104%2C+2023%2E)
8. W. Huang, P. Abbeel, D. Pathak, and I. Mordatch. [Language models as zero-shot planners: Extracting actionable knowledge for embodied agents](https://md.research.elamur.ai/free/en/papers/huang-2022-language-models-zero-shot-planners/). In International Conference on Machine Learning, pages 9118–9147. PMLR, 2022.
9. W. Huang, F. Xia, T. Xiao, H. Chan, J. Liang, P. Florence, A. Zeng, J. Tompson, I. Mordatch, Y. Chebotar, et al. Inner monologue: Embodied reasoning through planning with language models. arXiv preprint arXiv:2207.05608, 2022. [find](https://scholar.google.com/scholar?q=W%2E+Huang%2C+F%2E+Xia%2C+T%2E+Xiao%2C+H%2E+Chan%2C+J%2E+Liang%2C+P%2E+Florence%2C+A%2E+Zeng%2C+J%2E+Tompson%2C+I%2E+Mordatch%2C+Y%2E+Chebotar%2C+et+al%2E+Inner+monologue%3A+Embodied+reasoning+through+planning+with+language+models%2E+arXiv+prepri)
10. A. Kanervisto, S. Milani, K. Ramanauskas, N. Topin, Z. Lin, J. Li, J. Shi, D. Ye, Q. Fu, W. Yang, et al. Minerl diamond 2021 competition: Overview, results, and lessons learned. NeurIPS 2021 Competitions and Demonstrations Track, pages 13–28, 2022. [find](https://scholar.google.com/scholar?q=A%2E+Kanervisto%2C+S%2E+Milani%2C+K%2E+Ramanauskas%2C+N%2E+Topin%2C+Z%2E+Lin%2C+J%2E+Li%2C+J%2E+Shi%2C+D%2E+Ye%2C+Q%2E+Fu%2C+W%2E+Yang%2C+et+al%2E+Minerl+diamond+2021+competition%3A+Overview%2C+results%2C+and+lessons+learned%2E+NeurIPS+2021+Competiti)
11. I. Kanitscheider, J. Huizinga, D. Farhi, W. H. Guss, B. Houghton, R. Sampedro, P. Zhokhov, B. Baker, A. Ecoffet, J. Tang, et al. Multi-task curriculum learning in a complex, visual, hard-exploration domain: Minecraft. arXiv preprint arXiv:2106.14876, 2021. — [arXiv:2106.14876](https://arxiv.org/abs/2106.14876) [find](https://scholar.google.com/scholar?q=I%2E+Kanitscheider%2C+J%2E+Huizinga%2C+D%2E+Farhi%2C+W%2E+H%2E+Guss%2C+B%2E+Houghton%2C+R%2E+Sampedro%2C+P%2E+Zhokhov%2C+B%2E+Baker%2C+A%2E+Ecoffet%2C+J%2E+Tang%2C+et+al%2E+Multi%2Dtask+curriculum+learning+in+a+complex%2C+visual%2C+hard%2Dexploration+d)
12. M. Li, F. Song, B. Yu, H. Yu, Z. Li, F. Huang, and Y. Li. Api-bank: A benchmark for tool-augmented llms. arXiv preprint arXiv:2304.08244, 2023. — [arXiv:2304.08244](https://arxiv.org/abs/2304.08244) [find](https://scholar.google.com/scholar?q=M%2E+Li%2C+F%2E+Song%2C+B%2E+Yu%2C+H%2E+Yu%2C+Z%2E+Li%2C+F%2E+Huang%2C+and+Y%2E+Li%2E+Api%2Dbank%3A+A+benchmark+for+tool%2Daugmented+llms%2E+arXiv+preprint+arXiv%3A2304%2E08244%2C+2023%2E+%E2%80%94+%5BarXiv%3A2304%2E08244%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2304%2E08244%29)
13. J. Liang, W. Huang, F. Xia, P. Xu, K. Hausman, B. Ichter, P. Florence, and A. Zeng. Code as policies: Language model programs for embodied control. arXiv preprint arXiv:2209.07753, 2022. [find](https://scholar.google.com/scholar?q=J%2E+Liang%2C+W%2E+Huang%2C+F%2E+Xia%2C+P%2E+Xu%2C+K%2E+Hausman%2C+B%2E+Ichter%2C+P%2E+Florence%2C+and+A%2E+Zeng%2E+Code+as+policies%3A+Language+model+programs+for+embodied+control%2E+arXiv+preprint+arXiv%3A2209%2E07753%2C+2022%2E)
14. Z. Lin, J. Li, J. Shi, D. Ye, Q. Fu, and W. Yang. Juewu-mc: Playing minecraft with sample-efficient hierarchical reinforcement learning. arXiv preprint arXiv:2112.04907, 2021. — [arXiv:2112.04907](https://arxiv.org/abs/2112.04907) [find](https://scholar.google.com/scholar?q=Z%2E+Lin%2C+J%2E+Li%2C+J%2E+Shi%2C+D%2E+Ye%2C+Q%2E+Fu%2C+and+W%2E+Yang%2E+Juewu%2Dmc%3A+Playing+minecraft+with+sample%2Defficient+hierarchical+reinforcement+learning%2E+arXiv+preprint+arXiv%3A2112%2E04907%2C+2021%2E+%E2%80%94+%5BarXiv%3A2112%2E04907%5D%28htt)
15. H. Mao, C. Wang, X. Hao, Y. Mao, Y. Lu, C. Wu, J. Hao, D. Li, and P. Tang. Seihai: A sample-efficient hierarchical ai for the minerl competition. In Distributed Artificial Intelligence: Third International Conference, DAI 2021, Shanghai, China, December 17–18, 2021, Proceedings 3, pages 38–51. Sprin… [find](https://scholar.google.com/scholar?q=H%2E+Mao%2C+C%2E+Wang%2C+X%2E+Hao%2C+Y%2E+Mao%2C+Y%2E+Lu%2C+C%2E+Wu%2C+J%2E+Hao%2C+D%2E+Li%2C+and+P%2E+Tang%2E+Seihai%3A+A+sample%2Defficient+hierarchical+ai+for+the+minerl+competition%2E+In+Distributed+Artificial+Intelligence%3A+Third+Internat)
16. Y. Matsuo, Y. LeCun, M. Sahani, D. Precup, D. Silver, M. Sugiyama, E. Uchibe, and J. Morimoto. Deep learning, reinforcement learning, and world models. Neural Networks, 2022. [find](https://scholar.google.com/scholar?q=Y%2E+Matsuo%2C+Y%2E+LeCun%2C+M%2E+Sahani%2C+D%2E+Precup%2C+D%2E+Silver%2C+M%2E+Sugiyama%2C+E%2E+Uchibe%2C+and+J%2E+Morimoto%2E+Deep+learning%2C+reinforcement+learning%2C+and+world+models%2E+Neural+Networks%2C+2022%2E)
17. S. Milani, N. Topin, B. Houghton, W. H. Guss, S. P. Mohanty, K. Nakata, O. Vinyals, and N. S. Kuno. Retrospective analysis of the 2019 minerl competition on sample efficient reinforcement learning. In NeurIPS 2019 Competition and Demonstration Track, pages 203–214. PMLR, 2020. [find](https://scholar.google.com/scholar?q=S%2E+Milani%2C+N%2E+Topin%2C+B%2E+Houghton%2C+W%2E+H%2E+Guss%2C+S%2E+P%2E+Mohanty%2C+K%2E+Nakata%2C+O%2E+Vinyals%2C+and+N%2E+S%2E+Kuno%2E+Retrospective+analysis+of+the+2019+minerl+competition+on+sample+efficient+reinforcement+learning%2E+In)
18. S. Milani, A. Kanervisto, K. Ramanauskas, S. Schulhoff, B. Houghton, S. Mohanty, B. Galbraith, K. Chen, Y. Song, T. Zhou, et al. Towards solving fuzzy tasks with human feedback: A retrospective of the minerl basalt 2022 competition. arXiv preprint arXiv:2303.13512, 2023. — [arXiv:2303.13512](https://arxiv.org/abs/2303.13512) [find](https://scholar.google.com/scholar?q=S%2E+Milani%2C+A%2E+Kanervisto%2C+K%2E+Ramanauskas%2C+S%2E+Schulhoff%2C+B%2E+Houghton%2C+S%2E+Mohanty%2C+B%2E+Galbraith%2C+K%2E+Chen%2C+Y%2E+Song%2C+T%2E+Zhou%2C+et+al%2E+Towards+solving+fuzzy+tasks+with+human+feedback%3A+A+retrospective+of+the)
19. T. Schick, J. Dwivedi-Yu, R. Dessì, R. Raileanu, M. Lomeli, L. Zettlemoyer, N. Cancedda, and T. Scialom. [Toolformer: Language models can teach themselves to use tools](https://md.research.elamur.ai/free/en/papers/schick-2023-toolformer-language-models-can-teach/). arXiv preprint arXiv:2302.04761, 2023.
20. Y. Shen, K. Song, X. Tan, D. Li, W. Lu, and Y. Zhuang. Hugginggpt: Solving ai tasks with chatgpt and its friends in huggingface. arXiv preprint arXiv:2303.[17580, 2023](https://md.research.elamur.ai/free/en/papers/shen-2023-hugginggpt-solving-ai-tasks-chatgpt/).
21. I. Singh, V. Blukis, A. Mousavian, A. Goyal, D. Xu, J. Tremblay, D. Fox, J. Thomason, and A. Garg. [Progprompt: Generating situated robot task plans using large language models](https://md.research.elamur.ai/free/en/papers/singh-2022-progprompt-generating-situated-robot-task/). arXiv preprint arXiv:2209.11302, 2022.
22. A. Skrynnik, A. Staroverov, E. Aitygulov, K. Aksenov, V. Davydov, and A. I. Panov. Hierarchical deep q-network from imperfect demonstrations in minecraft. Cognitive Systems Research, 65:74–78, 2021. [find](https://scholar.google.com/scholar?q=A%2E+Skrynnik%2C+A%2E+Staroverov%2C+E%2E+Aitygulov%2C+K%2E+Aksenov%2C+V%2E+Davydov%2C+and+A%2E+I%2E+Panov%2E+Hierarchical+deep+q%2Dnetwork+from+imperfect+demonstrations+in+minecraft%2E+Cognitive+Systems+Research%2C+65%3A74%E2%80%9378%2C+2021%2E)
23. O. E. L. Team, A. Stooke, A. Mahajan, C. Barros, C. Deck, J. Bauer, J. Sygnowski, M. Trebacz, M. Jaderberg, M. Mathieu, et al. Open-ended learning leads to generally capable agents. arXiv preprint arXiv:2107.12808, 2021. — [arXiv:2107.12808](https://arxiv.org/abs/2107.12808) [find](https://scholar.google.com/scholar?q=O%2E+E%2E+L%2E+Team%2C+A%2E+Stooke%2C+A%2E+Mahajan%2C+C%2E+Barros%2C+C%2E+Deck%2C+J%2E+Bauer%2C+J%2E+Sygnowski%2C+M%2E+Trebacz%2C+M%2E+Jaderberg%2C+M%2E+Mathieu%2C+et+al%2E+Open%2Dended+learning+leads+to+generally+capable+agents%2E+arXiv+preprint+arX)
24. C. Tessler, S. Givony, T. Zahavy, D. Mankowitz, and S. Mannor. A deep hierarchical approach to lifelong learning in minecraft. In Proceedings of the AAAI conference on artificial intelligence, 2017. [find](https://scholar.google.com/scholar?q=C%2E+Tessler%2C+S%2E+Givony%2C+T%2E+Zahavy%2C+D%2E+Mankowitz%2C+and+S%2E+Mannor%2E+A+deep+hierarchical+approach+to+lifelong+learning+in+minecraft%2E+In+Proceedings+of+the+AAAI+conference+on+artificial+intelligence%2C+2017%2E)
25. Z. Wang, S. Cai, A. Liu, X. Ma, and Y. Liang. [Describe, explain, plan and select: Interactive planning with large language models enables open-world multi-task agents](https://md.research.elamur.ai/free/en/papers/wang-2023-describe-explain-plan-select-interactive/). arXiv preprint arXiv:2302.01560, 2023.
26. J. Wei, X. Wang, D. Schuurmans, M. Bosma, E. Chi, Q. Le, and D. Zhou. Chain of thought prompting elicits reasoning in large language models. arXiv preprint arXiv:2201.[11903, 2022](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/).
27. Wikipedia contributors. Minecraft — Wikipedia, the free encyclopedia. [https://en.wikipedia.org/w/index.php?title=Minecraft&oldid=1155148900](https://en.wikipedia.org/w/index.php?title=Minecraft&oldid=1155148900), 2023. [↗](https://en.wikipedia.org/w/index.php?title=Minecraft&oldid=1155148900)
28. H. Yuan, C. Zhang, H. Wang, F. Xie, P. Cai, H. Dong, and Z. Lu. Plan4mc: Skill reinforcement learning and planning for open-world minecraft tasks. arXiv preprint arXiv:2303.16563, 2023. — [arXiv:2303.16563](https://arxiv.org/abs/2303.16563) [find](https://scholar.google.com/scholar?q=H%2E+Yuan%2C+C%2E+Zhang%2C+H%2E+Wang%2C+F%2E+Xie%2C+P%2E+Cai%2C+H%2E+Dong%2C+and+Z%2E+Lu%2E+Plan4mc%3A+Skill+reinforcement+learning+and+planning+for+open%2Dworld+minecraft+tasks%2E+arXiv+preprint+arXiv%3A2303%2E16563%2C+2023%2E+%E2%80%94+%5BarXiv%3A2303%2E)

*Updated 2 November 2026*