Asia
A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptation
Runzhe Yang, Xingyuan Sun, Karthik Narasimhan
Neural Information Processing Systems http://nips.cc/
Leveraging sparse and shared feature activations for disentangled representation learning
However, this is not always the case, as different tasks can compete with each other and lead to weaker models.
Leveraging sparse and shared feature activations for disentangled representation learning
However, this is not always the case, as different tasks can compete with each other and lead to weaker models.
Leveraging Environment Interaction for Automated PDDL Translation and Planning with Large Language Models
We achieve an average task solve rate of 66% compared to a 29% solve rate by GPT -4's intrinsic planning with chain-of-thought prompting.
Learning Robust Options by Conditional Value at Risk Optimization
Takuya Hiraoka, Takahisa Imagawa, Tatsuya Mori, Takashi Onishi, Yoshimasa Tsuruoka
In the reinforcement learning context, anOption means a temporally extended sequence of actions [30],andisregarded asuseful formanypurposes, such asspeeding uplearning, transferring skills across domains, and solving long-term planning problems.
Certification of Distributional Individual Fairness
To combat this, there has been a surge of interest in algorithmic fairness metrics (Mehrabi et al., 2021).
A Regression Approach to Learning Augmented Online Algorithms
K. Anand, R. Ge, A. Kumar, D. Panigrahi
A recent trend in online algorithms has seen the use of future predictions generated by ML techniques to bypass pessimistic worst-case lower bounds.
d2cc447db9e56c13b993c11b45956281-Paper-Conference.pdf
A naiveimplementation of this approach leads to the dynamic component taking over the static one as the representation of the former is inherently more general and prone to overfitting.
