We have 3 of 14 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
This paper proposes NeSyAM, a novel neurosymbolic modeling paradigm for action model learning under partial observability, and presents a unified variational framework for theoretically analysing the limitations of existing methods compared to this proposed approach.
A new training and inference algorithm inspired by parallel-tempering Markov chain Monte Carlo methods is developed, which is named parallel noising and allows NMLNs to match the performance of specialized text-based recurrent models when generating small molecular structures.
This work presents a novel world model formulation where the reward prediction only depends on a subset of structured, symbolic components of the whole latent state, and demonstrates the strong generalisation properties of this approach over purely neural methods.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
