Publikationen von T Saanum
Alle Typen
Zeitschriftenartikel (1)
1.
Zeitschriftenartikel
26 (4), S. 615 - 626 (2023)
Hippocampal spatio-predictive cognitive maps adaptively guide reward generalization. Nature Neuroscience Konferenzbeitrag (5)
2.
Konferenzbeitrag
Evaluating alignment between humans and neural network representations in image-based learning tasks. In: Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024). Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024), Vancouver, Canada, 11. Dezember 2024 - 15. Dezember 2024. (2024)
3.
Konferenzbeitrag
Reinforcement Learning with Simple Sequence Priors. In: Advances in Neural Information Processing Systems 36: 37th Conference on Neural Information Processing Systems (NeurIPS 2023), 2710, S. 61985 - 62005 (Hg. Oh, A.; Naumann, T.; Globerson, A.; Saenko, K.; Hardt, M. et al.). Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023), New Orleans, LA, USA, 10. Dezember 2023 - 16. Dezember 2023. Curran, Red Hook, NY, USA (2024)
4.
Konferenzbeitrag
Decision-Making with Naturalistic Options. In: 44th Annual Meeting of the Cognitive Science Society (CogSci 2022): Cognitive Diversity, S. 976 - 982 (Hg. Culbertson, J.; Perfors, A.; Rabagliati, H.; Ramenzoni, V.). 44th Annual Meeting of the Cognitive Science Society (CogSci 2022): Cognitive Diversity, Toronto, Canada, 27. Juli 2022 - 30. Juli 2022. (2022)
5.
Konferenzbeitrag
Probing Compositional Inference in Natural and Artificial Agents. In: 5th Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM 2022), 1.67, S. 275 - 279. 5th Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM 2022), Providence, RI, USA, 08. Juni 2022 - 11. Juni 2022. (2022)
6.
Konferenzbeitrag
Compositional generalization in multi-armed bandits. In: 43rd Annual Conference of the Cognitive Science Society (CogSci 2021): Workshop 2 Using Games to Understand Intelligence, S. 1320 - 1326. 43rd Annual Conference of the Cognitive Science Society (CogSci 2021), Wien, Austria, 26. Juli 2021 - 29. Juli 2021. Curran, Red Hook, NY, USA (2021)
Poster (2)
7.
Poster
Learning parsimonious dynamics for state abstraction and navigation. Computational and Systems Neuroscience Meeting (COSYNE 2023), Montreal, Quebec, Canada (2023)
8.
Poster
Hippocampal spatio-temporal cognitive maps adaptively guide reward generalization. Computational and Systems Neuroscience Meeting (COSYNE 2022), Lisboa, Portugal (2022)
Preprint (6)
9.
Preprint
Centaur: a foundation model of human cognition. (eingereicht)
10.
Preprint
Sparse Autoencoders Reveal Temporal Difference Learning in Large Language Models. (eingereicht)
11.
Preprint
Next state prediction gives rise to entangled, yet compositional representations of objects. (eingereicht)
12.
Preprint
Zero-shot compositional reinforcement learning in humans. (eingereicht)
13.
Preprint
Language Aligned Visual Representations Predict Human Behavior in Naturalistic Learning Tasks. (eingereicht)
14.
Preprint
Learning Parsimonious Dynamics for Generalization in Reinforcement Learning. (eingereicht)