latplan

: https://arxiv.org/abs/1902.08093 . Asai has released code for earlier papers on github: "LatPlan : A domain-independent, image-based classical planner". https://github.com/guicho271828/latplan it reads as if the code for [1] may be open-sourced in future "Asai, M.: 2019. Unsupervised Grounding of Plannable First-Order Logic Representation from Images (code not yet available) " [+] research-quality, i.e., in whatever random state the prototype code it happens to be in, without any guarantees about it compiling, or running, or behaving correctly, having an automated test suite, or whatever. in all of these cases, it is _technically_ trivial to make it available to the wider research community

o accommodate the workflow in machine learning. For a neural-symbolic task, personally, Lisp is best in this space (I don't try to repeat why, because there are plenty of articles on it.), with Julia being a contender. I am also interested in adding the compile time type/shape checking on the deep learning code, since python debugging is painful (just a personal opinion -- not intending to start a war here). By the way, I made the first prototype of this lib in 3 days, and am working on improving it for 3 month (for other ML projects). [1] https://medium.com/@MITIBMLab/the-shared-history-and-vision-... [2] https://github.com/guicho271828/latplan [3] AAAI18 presentation at : https://asai-research-presentation.github.io/2018-2-5-aaai/ [4] AAAI18 paper : Classical Planning in Deep Latent Space: Bridging the Subsymbolic-Symbolic Boundary, https://arxiv.org/abs/1705.00154 [5] Follow-up papers (ICAPS2019) : https://arxiv.org/abs/1903.11277 [6] Follow-up papers (ICAPS2019), extension to first order logic : https://arxiv.org/abs/1902.08093 [7] Learning Plannable Representations with Causal InfoGAN, https://arxiv.org/abs/1807.09341v1