Optimization
Failure-Aware Gaussian Process Optimization with Regret Bounds
In addition, since only the binary failure can be obtained, the number of latent constraints is also unknown.
Failure-Aware Gaussian Process Optimization with Regret Bounds
In addition, since only the binary failure can be obtained, the number of latent constraints is also unknown.
AT oolkit for Reliable Benchmarking and Research in Multi-Objective Reinforcement Learning
There are several reasons why reproducibility is often a challenge in RL.
Time-Reversed Dissipation Induces Duality Between Minimizing Gradient Norm and Function Value
In convex optimization, first-order optimization methods efficiently minimizing function values have been a central subject study since Nesterov's seminal work
Self-Supervised Learning of Representations for Space Generates Multi-Modular Grid Cells
To solve the spatial problems of mapping, localization and navigation, the mammalian lineage has developed striking spatial representations.
Iteratively Learn Diverse Strategies with State Distance Information
In addition, we examine two common computation frameworks for this problem, i.e., population-based training (PBT) and iterative learning
Generalized test utilities for long-tail performance in extreme multi-label classification
Erik Schultheis, Marek Wydmuch, Wojciech Kotłowski, Rohit Babbar, Krzysztof Dembczyński
However, it is often argued that correct predictions in the tail are more "interesting" or "rewarding," but the community has not yet settled on a metric capturing this intuitive concept.