2026-04-27-revisiting-the-nle

assets/bibliography/2026-04-27-revisiting-the-nle.bib

@@ -0,0 +1,90 @@
+@article{samvelyan2021minihack,
+  title={Minihack the planet: A sandbox for open-ended reinforcement learning research},
+  author={Samvelyan, Mikayel and Kirk, Robert and Kurin, Vitaly and Parker-Holder, Jack and Jiang, Minqi and Hambro, Eric and Petroni, Fabio and K{\"u}ttler, Heinrich and Grefenstette, Edward and Rockt{\"a}schel, Tim},
+  journal={arXiv preprint arXiv:2109.13202},
+  year={2021}
+}
+
+@article{zheng2024online,
+  title={Online intrinsic rewards for decision making agents from large language model feedback},
+  author={Zheng, Qinqing and Henaff, Mikael and Zhang, Amy and Grover, Aditya and Amos, Brandon},
+  journal={arXiv preprint arXiv:2410.23022},
+  year={2024}
+}
+
+@article{henaff2025scalable,
+  title={Scalable Option Learning in High-Throughput Environments},
+  author={Henaff, Mikael and Fujimoto, Scott and Matthews, Michael and Rabbat, Michael},
+  journal={arXiv preprint arXiv:2509.00338},
+  year={2025}
+}
+
+@article{klissarov2024maestromotif,
+  title={Maestromotif: Skill design from artificial intelligence feedback},
+  author={Klissarov, Martin and Henaff, Mikael and Raileanu, Roberta and Sodhani, Shagun and Vincent, Pascal and Zhang, Amy and Bacon, Pierre-Luc and Precup, Doina and Machado, Marlos C and D'Oro, Pierluca},
+  journal={arXiv preprint arXiv:2412.08542},
+  year={2024}
+}
+
+@article{klissarov2023motif,
+  title={Motif: Intrinsic motivation from artificial intelligence feedback},
+  author={Klissarov, Martin and D'Oro, Pierluca and Sodhani, Shagun and Raileanu, Roberta and Bacon, Pierre-Luc and Vincent, Pascal and Zhang, Amy and Henaff, Mikael},
+  journal={arXiv preprint arXiv:2310.00166},
+  year={2023}
+}
+
+@article{tuyls2023scaling,
+  title={Scaling laws for imitation learning in single-agent games},
+  author={Tuyls, Jens and Madeka, Dhruv and Torkkola, Kari and Foster, Dean and Narasimhan, Karthik and Kakade, Sham},
+  journal={arXiv preprint arXiv:2307.09423},
+  year={2023}
+}
+
+@article{piterbarg2023nethack,
+  title={Nethack is hard to hack},
+  author={Piterbarg, Ulyana and Pinto, Lerrel and Fergus, Rob},
+  journal={Advances in Neural Information Processing Systems},
+  volume={36},
+  pages={37540--37566},
+  year={2023}
+}
+
+@inproceedings{hambro2022insights,
+  title={Insights from the neurips 2021 nethack challenge},
+  author={Hambro, Eric and Mohanty, Sharada and Babaev, Dmitrii and Byeon, Minwoo and Chakraborty, Dipam and Grefenstette, Edward and Jiang, Minqi and Daejin, Jo and Kanervisto, Anssi and Kim, Jongmin and others},
+  booktitle={NeurIPS 2021 Competitions and Demonstrations Track},
+  pages={41--52},
+  year={2022},
+  organization={PMLR}
+}
+
+@article{wolczyk2024fine,
+  title={Fine-tuning reinforcement learning models is secretly a forgetting mitigation problem},
+  author={Wo{\l}czyk, Maciej and Cupia{\l}, Bart{\l}omiej and Ostaszewski, Mateusz and Bortkiewicz, Micha{\l} and Zaj{\k{a}}c, Micha{\l} and Pascanu, Razvan and Kuci{\'n}ski, {\L}ukasz and Mi{\l}o{\'s}, Piotr},
+  journal={arXiv preprint arXiv:2402.02868},
+  year={2024}
+}
+
+@article{hambro2022dungeons,
+  title={Dungeons and data: A large-scale nethack dataset},
+  author={Hambro, Eric and Raileanu, Roberta and Rothermel, Danielle and Mella, Vegard and Rockt{\"a}schel, Tim and K{\"u}ttler, Heinrich and Murray, Naila},
+  journal={Advances in Neural Information Processing Systems},
+  volume={35},
+  pages={24864--24878},
+  year={2022}
+}
+
+@article{kuttler2020nethack,
+  title={The nethack learning environment},
+  author={K{\"u}ttler, Heinrich and Nardelli, Nantas and Miller, Alexander and Raileanu, Roberta and Selvatici, Marco and Grefenstette, Edward and Rockt{\"a}schel, Tim},
+  journal={Advances in Neural Information Processing Systems},
+  volume={33},
+  pages={7671--7684},
+  year={2020}
+}
+@article{paglieri2024balrog,
+  title={Balrog: Benchmarking agentic llm and vlm reasoning on games},
+  author={Paglieri, Davide and Cupia{\l}, Bart{\l}omiej and Coward, Samuel and Piterbarg, Ulyana and Wolczyk, Maciej and Khan, Akbir and Pignatelli, Eduardo and Kuci{\'n}ski, {\L}ukasz and Pinto, Lerrel and Fergus, Rob and others},
+  journal={arXiv preprint arXiv:2411.13543},
+  year={2024}
+}