Fetching the paper…
Reading the bibliography…
We design and conduct a simple experiment to study whether neural networks can perform several steps of approximate reasoning in a fixed dimensional latent space.
Model-based reinforcement learning for Atari
Kaiser, L., Babaeizadeh, M., Milos, P., Osinski, B., Campbell, R. H., Czechowski, K., Erhan, D., Finn, C., Kozakowski, P., Levine, S., et al. (2019) · 1903
Earlier work this paper cites.
Learning to reason in large theories without imitation
Bansal, K., Loos, S. M., Rabe, M. N., and Szegedy, C. (2019a) · 1905
Earlier work this paper cites.
Graph representations for higher-order logic and theorem proving
Paliwal, A., Loos, S., Rabe, M., Bansal, K., and Szegedy, C. (2019) · 1905
Earlier work this paper cites.
HOL Light: A tutorial introduction
Harrison, J. (1996) · 1996
Earlier work this paper cites.
Formal proof–the four-color theorem
Gonthier, G. (2008) · 2008
Earlier work this paper cites.
Hol (y) hammer: Online atp service for hol light
Kaliszyk, C. and Urban, J. (2015) · 2015
Earlier work this paper cites.
Action-conditional video prediction using deep networks in Atari games
Oh, J., Guo, X., Lee, H., Lewis, R. L., and Singh, S. (2015) · 2015
Earlier work this paper cites.
Deepmath-deep sequence models for premise selection
Alemi, A. A., Chollet, F., Irving, G., Eén, N., Szegedy, C., and Urban, J. (2016) · 2016
Cited alongside, same era.
Recurrent environment simulators
Chiappa, S., Racanière, S., Wierstra, D., and Mohamed, S. (2017) · 2017
Cited alongside, same era.
Learning to act by predicting the future
Dosovitskiy, A. and Koltun, V. (2017) · 2017
Cited alongside, same era.
Tactictoe: Learning to reason with HOL4 tactics
Gauthier, T., Kaliszyk, C., and Urban, J. (2017) · 2017
Cited alongside, same era.
A formal proof of the Kepler conjecture
Hales, T., Adams, M., Bauer, G., Dang, T. D., Harrison, J., Le Truong, H., Kaliszyk, C., Magron, V., McLaughlin, S., Nguyen, T. T., et al. (2017) · 2017
Cited alongside, same era.
Deep network guided proof search
Loos, S., Irving, G., Szegedy, C., and Kaliszyk, C. (2017) · 2017
Using state predictions for value regularization in curiosity driven deep reinforcement learning
Brunner, G., Fritsche, M., Richter, O., and Wattenhofer, R. (2018) · 2018
Later among the works it cites.
Recurrent world models facilitate policy evolution
Ha, D. and Schmidhuber, J. (2018) · 2018
Later among the works it cites.
Learning heuristics for automated reasoning through deep reinforcement learning
Lederman, G., Rabe, M. N., and Seshia, S. A. (2018) · 2018
Later among the works it cites.
HOList: An environment for machine learning of higher-order theorem proving
Bansal, K., Loos, S. M., Rabe, M. N., Szegedy, C., and Wilcox, S. (2019b) · 2019
Closest in time.
Accessed: 2019/09/23
HOL Light Rewrite Tactic Reference · 2019
Closest in time.
Can neural networks learn symbolic rewriting?
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Cited alongside, same era.
Premise selection for theorem proving by deep graph embedding
Wang, M., Tang, Y., Wang, J., and Deng, J. (2017) · 2017
Cited alongside, same era.
The Coq Proof Assistant
Coq
Cited in the paper.
Piotrowski, B., Brown, C., Urban, J., and Kaliszyk, C. (2019) · 2019
Closest in time.