Dataset condensation for recommendation
Training recommendation models on large datasets often requires significant time and
computational resources. Consequently, an emergent imperative has arisen to construct …
computational resources. Consequently, an emergent imperative has arisen to construct …
Generalized data distribution iteration
To obtain higher sample efficiency and superior final performance simultaneously has been
one of the major challenges for deep reinforcement learning (DRL). Previous work could …
one of the major challenges for deep reinforcement learning (DRL). Previous work could …
A review for deep reinforcement learning in atari: Benchmarks, challenges, and solutions
J Fan - arXiv preprint arXiv:2112.04145, 2021 - arxiv.org
The Arcade Learning Environment (ALE) is proposed as an evaluation platform for
empirically assessing the generality of agents across dozens of Atari 2600 games. ALE …
empirically assessing the generality of agents across dozens of Atari 2600 games. ALE …
Differentiable arbitrating in zero-sum markov games
We initiate the study of how to perturb the reward in a zero-sum Markov game with two
players to induce a desirable Nash equilibrium, namely arbitrating. Such a problem admits a …
players to induce a desirable Nash equilibrium, namely arbitrating. Such a problem admits a …
Optimization in Deep Learning: Loss Landscape, Optimizer Dynamics, and Bi-Level Settings
J Wang - 2024 - search.proquest.com
Abstract Machine learning has witnessed remarkable advancements in recent years,
transforming various industries and domains. Central to the success of machine learning …
transforming various industries and domains. Central to the success of machine learning …