@misc{slap,
  title = {SLAP: Shortcut Learning for Abstract Planning},
  author = {Y. Isabel Liu and Bowen Li and Benjamin Eysenbach and Tom Silver},
  year = {2026},
  note = {ICLR 2026},
  url = {https://arxiv.org/abs/2511.01107}
}

@misc{symbols,
  title = {From Skills to Symbols: Learning Symbolic Representations for Abstract High-Level Planning},
  author = {George Konidaris and Leslie Pack Kaelbling and Tomas Lozano-Perez},
  year = {2018},
  note = {JAIR 61},
  url = {https://cs.brown.edu/people/gdk/pubs/orig_sym_jair.pdf}
}

@misc{dads,
  title = {Dynamics-Aware Unsupervised Discovery of Skills},
  author = {Archit Sharma and Shixiang Gu and Sergey Levine and Vikash Kumar and Karol Hausman},
  year = {2020},
  note = {ICLR 2020},
  url = {https://arxiv.org/abs/1907.01657}
}

@misc{plan2explore,
  title = {Planning to Explore via Self-Supervised World Models},
  author = {Ramanan Sekar and Oleh Rybkin and Kostas Daniilidis and Pieter Abbeel and Danijar Hafner and Deepak Pathak},
  year = {2020},
  note = {ICML 2020},
  url = {https://proceedings.mlr.press/v119/sekar20a.html}
}

@misc{tople,
  title = {Task-Optimal Exploration in Linear Dynamical Systems},
  author = {Andrew J. Wagenmaker and Max Simchowitz and Kevin Jamieson},
  year = {2021},
  note = {ICML 2021},
  url = {https://proceedings.mlr.press/v139/wagenmaker21a.html}
}

@misc{alpgmm,
  title = {Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environments},
  author = {Rémy Portelas and Cédric Colas and Katja Hofmann and Pierre-Yves Oudeyer},
  year = {2020},
  note = {CoRL 2019 · proceedings 2020},
  url = {https://proceedings.mlr.press/v100/portelas20a.html}
}

@misc{activeid,
  title = {Active Learning for Identification of Linear Dynamical Systems},
  author = {Andrew Wagenmaker and Kevin Jamieson},
  year = {2020},
  note = {COLT 2020},
  url = {https://proceedings.mlr.press/v125/wagenmaker20a.html}
}

@misc{rewardfree,
  title = {Reward-Free Exploration for Reinforcement Learning},
  author = {Chi Jin and Akshay Krishnamurthy and Max Simchowitz and Tiancheng Yu},
  year = {2020},
  note = {ICML 2020},
  url = {https://proceedings.mlr.press/v119/jin20d.html}
}

@misc{vime,
  title = {VIME: Variational Information Maximizing Exploration},
  author = {Rein Houthooft and Xi Chen and Yan Duan and John Schulman and Filip De Turck and Pieter Abbeel},
  year = {2016},
  note = {NeurIPS 2016},
  url = {https://arxiv.org/abs/1605.09674}
}

@misc{dsg,
  title = {Skill Discovery for Exploration and Planning using Deep Skill Graphs},
  author = {Akhil Bagaria and Jason K. Senthil and George Konidaris},
  year = {2021},
  note = {ICML 2021},
  url = {https://proceedings.mlr.press/v139/bagaria21a.html}
}

@misc{imgep,
  title = {Intrinsically Motivated Goal Exploration Processes with Automatic Curriculum Learning},
  author = {Sébastien Forestier and Rémy Portelas and Yoan Mollard and Pierre-Yves Oudeyer},
  year = {2022},
  note = {JMLR 23(152)},
  url = {https://www.jmlr.org/papers/v23/21-0808.html}
}

@misc{sgcrl,
  title = {A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals},
  author = {Grace Liu and Michael Tang and Benjamin Eysenbach},
  year = {2025},
  note = {ICLR 2025},
  url = {https://arxiv.org/abs/2408.05804}
}

@misc{demystifying,
  title = {Demystifying the Mechanisms Behind Emergent Exploration in Goal-conditioned RL},
  author = {Mahsa Bastankhah and Grace Liu and Dilip Arumugam and Thomas L. Griffiths and Benjamin Eysenbach},
  year = {2026},
  note = {ICLR 2026},
  url = {https://arxiv.org/abs/2510.14129}
}

@misc{temporal,
  title = {Temporal Representations for Exploration: Learning Complex Exploratory Behavior without Extrinsic Rewards},
  author = {Faisal Mohamed and Catherine Ji and Benjamin Eysenbach and Glen Berseth},
  year = {2026},
  note = {ICLR 2026},
  url = {https://arxiv.org/abs/2603.02008}
}

@misc{identifiable,
  title = {Skill Learning via Policy Diversity Yields Identifiable Representations for Reinforcement Learning},
  author = {Patrik Reizinger and Bálint Mucsányi and Siyuan Guo and Benjamin Eysenbach and Bernhard Schölkopf and Wieland Brendel},
  year = {2026},
  note = {ICLR 2026},
  url = {https://arxiv.org/abs/2507.14748}
}

@misc{controlmax,
  title = {Unifying Goal-Conditioned RL and Unsupervised Skill Learning via Control-Maximization},
  author = {Alireza Modirshanechi and Benjamin Eysenbach and Peter Dayan and Eric Schulz},
  year = {2026},
  note = {May 2026 preprint},
  url = {https://arxiv.org/abs/2605.06145}
}

@misc{sorb,
  title = {Search on the Replay Buffer: Bridging Planning and Reinforcement Learning},
  author = {Benjamin Eysenbach and Ruslan Salakhutdinov and Sergey Levine},
  year = {2019},
  note = {NeurIPS 2019},
  url = {https://arxiv.org/abs/1906.05253}
}

@misc{contrastive,
  title = {Contrastive Learning as Goal-Conditioned Reinforcement Learning},
  author = {Benjamin Eysenbach and Tianjun Zhang and Ruslan Salakhutdinov and Sergey Levine},
  year = {2022},
  note = {NeurIPS 2022},
  url = {https://arxiv.org/abs/2206.07568}
}

@misc{successor,
  title = {Successor Features for Transfer in Reinforcement Learning},
  author = {André Barreto and Will Dabney and Rémi Munos and Jonathan J. Hunt and Tom Schaul and Hado van Hasselt and David Silver},
  year = {2017},
  note = {NeurIPS 2017},
  url = {https://arxiv.org/abs/1606.05312}
}