arXiv research

MineRL Competition reduced reinforcement learning sample needs.

Kaggle competitions offer valuable insights for business forecasting.

New framework promotes reproducible, domain-agnostic reinforcement learning algorithms.

This work bridges competitive learning with gradient-based learning for faster feature extraction.

Study examines machine learning competitions' impact on AI development.

Adaptive learning rate improves FTRL's performance in online learning.

Combines gradient-based and competitive learning for unsupervised feature extraction.

Data competitions rely on real-time leaderboards to rank competitor entries and stimulate algorithm improvement. While such competitions have become quite popular and prevalent, particularly in supervised learning formats, their implementations by the host are highly variable. Without careful planning, a supervised lea…

Agents learn to outperform in trading by using past and current prices.

Machine learning competition predicts spacecraft collision risks.

Competition aims to develop sample-efficient reinforcement learning methods.

Challenge encourages reproducible deep learning methods.

State-space models win a forecasting competition for unstable data.

We organized a competition on Autonomous Lifelong Machine Learning with Drift that was part of the competition program of NeurIPS 2018. This data driven competition asked participants to develop computer programs capable of solving supervised learning problems where the i.i.d. assumption did not hold. Large data sets w…

Researchers improved Minecraft game performance using imitation learning.

In this paper, we propose AutoCompete, a highly automated machine learning framework for tackling machine learning competitions. This framework has been learned by us, validated and improved over a period of more than two years by participating in online machine learning competitions. It aims at minimizing human interf…

NeurIPS 2020 competition seeks to predict deep learning generalization.

This work tackles representation learning by introducing stochastic competition-based activations.

In this study, we investigate the use of global information to speed up the learning process and increase the cumulative rewards of reinforcement learning (RL) in competition tasks. Within the actor-critic RL, we introduce multiple cooperative critics from two levels of the hierarchy and propose a reinforcement learnin…

A fair reward system boosts participation in federated learning.

To accelerate research on adversarial examples and robustness of machine learning classifiers, Google Brain organized a NIPS 2017 competition that encouraged researchers to develop new methods to generate adversarial examples as well as to develop new ways to defend against them. In this chapter, we describe the struct…

LLMs can collude in market divisions, maximizing profits.

The paper improves competitive and dynamic regret bounds for smoothed online learning.

Kaggle chronicles 15 years of competitions, innovation, and data science.

Study predicts individual treatment effects in ride-sharing competitions.

The paper develops algorithms for competitive RL in partially observable MGs.

A new method for analyzing product competition using low-dimensional embeddings.

The ICML 2013 Workshop on Challenges in Representation Learning focused on three challenges: the black box learning challenge, the facial expression recognition challenge, and the multimodal learning challenge. We describe the datasets created for these challenges and summarize the results of the competitions. We provi…

New particle-based method improves semi-supervised learning robustness to label noise.

This paper presents the first two editions of Visual Doom AI Competition, held in 2016 and 2017. The challenge was to create bots that compete in a multi-player deathmatch in a first-person shooter (FPS) game, Doom. The bots had to make their decisions based solely on visual information, i.e., a raw screen buffer. To p…

New algorithms prove self-play can be effective in competitive RL.

Study shows how competition affects learning in matching markets, proving it's possible to balance stability, fairness, and regret.

Machine learning is often used in competitive scenarios: Participants learn and fit static models, and those models compete in a shared platform. The common assumption is that in order to win a competition one has to have the best predictive model, i.e., the model with the smallest out-sample error. Is that necessarily…

A drone catches another agile drone using competitive reinforcement learning.

Deep network learns Obstacle Tower challenge without human demonstrations.

Study shows competition feedback can make ML predictors biased towards specific user groups.

Develops a learning model predictive controller for competitive racing.

Deep learning has achieved remarkable successes in solving challenging reinforcement learning (RL) problems when dense reward function is provided. However, in sparse reward environment it still often suffers from the need to carefully shape reward function to guide policy optimization. This limits the applicability of…

Study liquidity provision with exogenous competition using a reference market maker.

Paper tackles AI driving competition challenges with mixed simulation and real-world data.

Paper studies competitive networks where teams aim to minimize their own objectives, adapting to each other's strategies.

Private cancer prediction model trained on federated genomic data.

Demand outstrips available resources in most situations, which gives rise to competition, interaction and learning. In this article, we review a broad spectrum of multi-agent models of competition (El Farol Bar problem, Minority Game, Kolkata Paise Restaurant problem, Stable marriage problem, Parking space problem and …

We develop a mean-field theory for multi-component ICA in high dimensions.

Improved model accuracy can reduce overall user accuracy in competitive markets.

Optimal learning for parametric prophet inequalities with exponential-type distributions

Autoencoders have been successful in learning meaningful representations from image datasets. However, their performance on text datasets has not been widely studied. Traditional autoencoders tend to learn possibly trivial representations of text documents due to their confounding properties such as high-dimensionality…

New study shows FTRL mechanism works with correlated events.