Minerl diamond 2021 competition: Overview, results, and lessons learned
A Kanervisto, S Milani… - NeurIPS 2021 …, 2022 - proceedings.mlr.press
Reinforcement learning competitions advance the field by providing appropriate scope and
support to develop solutions toward a specific problem. To promote the development of …
support to develop solutions toward a specific problem. To promote the development of …
Sparse representation for machine learning the properties of defects in 2D materials
N Kazeev, AR Al-Maeeni, I Romanov… - npj Computational …, 2023 - nature.com
Two-dimensional materials offer a promising platform for the next generation of (opto-)
electronic devices and other high technology applications. One of the most exciting …
electronic devices and other high technology applications. One of the most exciting …
Generative flow networks as entropy-regularized rl
The recently proposed generative flow networks (GFlowNets) are a method of training a
policy to sample compositional discrete objects with probabilities proportional to a given …
policy to sample compositional discrete objects with probabilities proportional to a given …
Nas-bench-nlp: neural architecture search benchmark for natural language processing
N Klyuchnikov, I Trofimov, E Artemova… - IEEE …, 2022 - ieeexplore.ieee.org
Neural Architecture Search (NAS) is a promising and rapidly evolving research area.
Training a large number of neural networks requires an exceptional amount of …
Training a large number of neural networks requires an exceptional amount of …
Grain boundary sliding and distortion on a nanosecond timescale induce trap states in CsPbBr 3: ab initio investigation with machine learning force field
Grain boundaries (GBs) in perovskite solar cells and optoelectronic devices are widely
regarded as detrimental defects that accelerate charge and energy losses through …
regarded as detrimental defects that accelerate charge and energy losses through …
Atomistic simulations of ettringite and its aqueous interfaces: Structure and properties revisited with the modified ClayFF force field
EV Tararushkin, VV Pisarev, AG Kalinichev - Cement and Concrete …, 2022 - Elsevier
Abstract Ettringite,(Ca 6 [Al (OH) 6] 2 [SO 4] 3· nH 2 O, n= 24–27), is one of the common
phases of cement and plays an important role in cement chemistry as the primary cause of …
phases of cement and plays an important role in cement chemistry as the primary cause of …
Findings of the the ruatd shared task 2022 on artificial text detection in russian
We present the shared task on artificial text detection in Russian, which is organized as a
part of the Dialogue Evaluation initiative, held in 2022. The shared task dataset includes …
part of the Dialogue Evaluation initiative, held in 2022. The shared task dataset includes …
Active learning for abstractive text summarization
Construction of human-curated annotated datasets for abstractive text summarization (ATS)
is very time-consuming and expensive because creating each instance requires a human …
is very time-consuming and expensive because creating each instance requires a human …
Scalable multi-agent model-based reinforcement learning
V Egorov, A Shpilman - arXiv preprint arXiv:2205.15023, 2022 - arxiv.org
Recent Multi-Agent Reinforcement Learning (MARL) literature has been largely focused on
Centralized Training with Decentralized Execution (CTDE) paradigm. CTDE has been a …
Centralized Training with Decentralized Execution (CTDE) paradigm. CTDE has been a …
On the periodic behavior of neural network training with batch normalization and weight decay
Training neural networks with batch normalization and weight decay has become a common
practice in recent years. In this work, we show that their combined use may result in a …
practice in recent years. In this work, we show that their combined use may result in a …