Learning with Value-Ramp
We study a learning principle based on the intuition of forming ramps. The agent tries to follow an increasing sequence of values until the agent meets a peak of reward. The resulting Value-Ramp algorithm is natural, easy to configure, and has a robust implementation with natural numbers.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Linear energy storage and flexibility model with ramp rate, ramping, deadline and capacity constraints
The power networks are evolving with increased active components such as energy storage and flexibility derived from loads such as electric vehicles, heat pumps, industrial processes, etc. Better models are needed to acc…
BenchmarkingFlexible Ramping Product Procurement in Day-Ahead Markets
Flexible ramping products (FRPs) emerge as a promising instrument for addressing steep and uncertain ramping needs through market mechanisms. Initial implementations of FRPs in North American electricity markets, however…
Chance constrained day-ahead robust flexibility needs assessment for low voltage distribution network
For market-based procurement of low voltage (LV) flexibility, DSOs identify the amount of flexibility needed for resolving probable distribution network (DN) voltage and thermal congestion. A framework is required to avo…
Making Risk Minimization Tolerant to Label Noise
In many applications, the training data, from which one needs to learn a classifier, is corrupted with label noise. Many standard algorithms such as SVM perform poorly in presence of label noise. In this paper we investi…
AGRAMPLIFIER: Defending Federated Learning Against Poisoning Attacks Through Local Update Amplification
The collaborative nature of federated learning (FL) poses a major threat in the form of manipulation of local training data and local updates, known as the Byzantine poisoning attack. To address this issue, many Byzantin…
Federated Learning