Zobrazeno 1 - 10
of 58
pro vyhledávání: '"Ernst, Damien"'
Publikováno v:
ICML Workshop on Next Generation of Sequence Modeling Architectures, 2024
Attention-based models such as Transformers and recurrent models like state space models (SSMs) have emerged as successful methods for autoregressive sequence modeling. Although both enable parallel training, none enable parallel generation due to th
Externí odkaz:
http://arxiv.org/abs/2407.08415
This study proposes a novel approach based on reinforcement learning (RL) to enhance the sorting efficiency of scrap metal using delta robots and a Pick-and-Place (PaP) process, widely used in the industry. We use three classical model-free RL algori
Externí odkaz:
http://arxiv.org/abs/2406.13453
Policy-gradient algorithms are effective reinforcement learning methods for solving control problems with continuous state and action spaces. To compute near-optimal policies, it is essential in practice to include exploration terms in the learning o
Externí odkaz:
http://arxiv.org/abs/2402.00162
We propose in this paper an optimal control framework for renewable energy communities (RECs) equipped with controllable assets. Such RECs allow its members to exchange production surplus through an internal market. The objective is to control their
Externí odkaz:
http://arxiv.org/abs/2401.16321
Achieving carbon neutrality is probably one of the most important challenges of the 21st century for our societies. Part of the solution to this challenge is to leverage renewable energies. However, these energy sources are often located far away fro
Externí odkaz:
http://arxiv.org/abs/2310.01964
We introduce IMP-MARL, an open-source suite of multi-agent reinforcement learning (MARL) environments for large-scale Infrastructure Management Planning (IMP), offering a platform for benchmarking the scalability of cooperative MARL methods in real-w
Externí odkaz:
http://arxiv.org/abs/2306.11551
In this work, we generalize the problem of learning through interaction in a POMDP by accounting for eventual additional information available at training time. First, we introduce the informed POMDP, a new learning paradigm offering a clear distinct
Externí odkaz:
http://arxiv.org/abs/2306.11488
Spiking neural networks are a type of artificial neural networks in which communication between neurons is only made of events, also called spikes. This property allows neural networks to make asynchronous and sparse computations and therefore drasti
Externí odkaz:
http://arxiv.org/abs/2306.03623
Direct policy optimization in reinforcement learning is usually solved with policy-gradient algorithms, which optimize policy parameters via stochastic gradient ascent. This paper provides a new theoretical interpretation and justification of these a
Externí odkaz:
http://arxiv.org/abs/2305.06851
Publikováno v:
PROCEEDINGS OF ECOS 2023 - THE 36TH INTERNATIONAL CONFERENCE ON EFFICIENCY, COST, OPTIMIZATION, SIMULATION AND ENVIRONMENTAL IMPACT OF ENERGY SYSTEMS 25-30 JUNE 2023, LAS PALMAS DE GRAN CANARIA, SPAIN
In this paper, we propose a multi-RREH (Remote Renewable Energy Hub) based optimization framework. This framework allows a valorization of CO2 using carbon capture technologies. This valorization is grounded on the idea that CO2 gathered from the atm
Externí odkaz:
http://arxiv.org/abs/2303.09454