We have 2 of 228 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.
It is shown that the vector representations of a variety of neural networks can be closely approximated with symbolic structures, providing a potential way to reconcile longstanding symbolic conceptions of intelligence with the vector-based nature of modern AI.
GFlowRL, a streamlined GFlowNet-style RL algorithm that removes the auxiliary partition network entirely while preserving the reward-distribution-matching objective, is proposed, and is the first GFlowNet-style RL algorithm to scale stably across both dense and sparse architectures.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
