Constraint-Based Reasoning
Reduced Policy Optimization for Continuous Control with Hard Constraints Shutong Ding 1 Jingya Wang 1 Yali Du2Y e Shi 1 1
Recent advances in constrained reinforcement learning (RL) have endowed reinforcement learning with certain safety guarantees.
Quantum Embedding of Knowledge for Reasoning
Dinesh Garg, Shajith Ikbal, Santosh K. Srivastava, Harit Vishwakarma, Hima Karanam, L Venkata Subramaniam
Neural Information Processing Systems http://nips.cc/
Hybrid-MST: A Hybrid Active Sampling Strategy for Pairwise Preference Aggregation
JING LI, Rafal Mantiuk, Junle Wang, Suiyi Ling, Patrick Le Callet
Neural Information Processing Systems http://nips.cc/
Controlling Continuous Relaxation for Combinatorial Optimization
Unsupervised learning (UL)-based solvers for combinatorial optimization (CO) train a neural network that generates a soft solution by directly optimizing the CO objective using a continuous relaxation strategy. These solvers offer several advantages over traditional methods and other learning-based methods, particularly for large-scale CO problems.
Optimal Algorithms for Online Convex Optimization with Adversarial Constraints
Surprisingly, the analysis is short and elegant.
Semi-Supervised Learning with Declaratively Specified Entropy Constraints
Haitian Sun, William W. Cohen, Lidong Bing
Neural Information Processing Systems http://nips.cc/
Streamlining Variational Inference for Constraint Satisfaction Problems
Aditya Grover, Tudor Achim, Stefano Ermon
Neural Information Processing Systems http://nips.cc/