arXiv research

This paper tackles RL in non-stationary environments, improving decision-making.

VR enables professionals to develop deep learning models by moving virtual objects.

Paper uses RL for high-level character control in 3D environments.

Building models, or maps, of robot environments is a highly active research area; however, most existing techniques construct unstructured maps and assume static environments. In this paper, we present an algorithm for learning object models of non-stationary objects found in office-type environments. Our algorithm exp…

WILD-SCAV benchmarks AI in complex 3D FPS environments.

A model is developed to study the effectiveness of innovation and its impact on structure creation and structure change on agent-based societies. The abstract model that is developed is easily adapted to any particular field. In any interacting environment, the agents receive something from the environment (the other a…

New approach transfers rewards learned in one environment to reinforcement learning in a new environment.

Deep RL for multi-agent autonomous driving in dynamic environments.

This paper introduces Dex, a reinforcement learning environment toolkit specialized for training and evaluation of continual learning methods as well as general reinforcement learning problems. We also present the novel continual learning method of incremental learning, where a challenging environment is solved using o…

New approach handles stochastic and partially-observable environments using discrete autoencoders and Monte Carlo tree search.

A machine learning environment for detecting autonomous vehicle corner cases.

Advantage amplification helps RL in slow-evolving latent-state environments.

Competition aims to develop sample-efficient reinforcement learning methods.

Competition aims to develop sample-efficient RL methods using human demonstrations.

Bayesian model for multi-environment prediction with latent variable changes.

Proposes ABIDES-Gym for financial markets simulation.

Develops HMRL for sparse reward RL problems, improving meta policy efficiency and transferability.

PSRL extension for continuing environments reduces regret.

Deep learning agent improves pedestrian navigation in urban environments.

PrototypeML simplifies neural network design and development.

Develops RL algorithm for lifelong non-stationary environments.

A new method for learning policies in multiple environments.

XRM discovers environments without human annotations for OOD methods.

Develops a risk-sensitive reinforcement learning framework for uncertain environments.

Estimator improves prediction with missing data in multi-environment settings.

New model predicts urban sprawl sensitivity from remote sensing data.

Survey of RL algorithms for dynamic environments.

Meta-learning agents excel at rapidly learning new tasks from open-ended task distributions; yet, they forget what they learn about each task as soon as the next begins. When tasks reoccur - as they do in natural environments - metalearning agents must explore again instead of immediately exploiting previously discover…

The behavioral dynamics of multi-agent systems have a rich and orderly structure, which can be leveraged to understand these systems, and to improve how artificial agents learn to operate in them. Here we introduce Relational Forward Models (RFM) for multi-agent learning, networks that can learn to make accurate predic…

Kernel-based methods exhibit well-documented performance in various nonlinear learning tasks. Most of them rely on a preselected kernel, whose prudent choice presumes task-specific prior information. Especially when the latter is not available, multi-kernel learning has gained popularity thanks to its flexibility in ch…

Jelly Bean World tests never-ending learning in complex environments.

GALA framework learns invariant graph representations via environment augmentation with minimal assumptions.

Deep RL agent improves lane changing in unpredictable traffic.

NetHack Learning Environment (NLE) tests RL algorithms, offering scalable, complex, and challenging gameplay.

Bayesian Invariant Prediction models stable features from multi-environment data.

Proposes ANN for more accurate path loss prediction in urban environments.

New methods improve prediction intervals across multiple environments.

There are great interests as well as many challenges in applying reinforcement learning (RL) to recommendation systems. In this setting, an online user is the environment; neither the reward function nor the environment dynamics are clearly defined, making the application of RL challenging. In this paper, we propose a …

This work develops agents to learn generalizable policies for dynamic network environments.

Develops model selection for bandits balancing adversarial and stochastic guarantees.

We describe theoretical bounds and a practical algorithm for teaching a model by demonstration in a sequential decision making environment. Unlike previous efforts that have optimized learners that watch a teacher demonstrate a static policy, we focus on the teacher as a decision maker who can dynamically choose differ…

Two adaptive algorithms improve tracking regret in dynamic expert advice problems.

Paper presents method for generating synthetic data to evaluate GPMs in complex environments.

New benchmark tests machine learning's ability to learn causal overhypotheses.

Safe-DRFS selects features robust to covariate shifts for reliable performance.

The design of robotic systems is largely dictated by our purely human intuition about how we perceive the world. This intuition has been proven incorrect with regard to a number of critical issues, such as visual change blindness. In order to develop truly autonomous robots, we must step away from this intuition and le…

Reinforcement learning (RL) agents optimize only the features specified in a reward function and are indifferent to anything left out inadvertently. This means that we must not only specify what to do, but also the much larger space of what not to do. It is easy to forget these preferences, since these preferences are …

The paper develops a method to learn navigation costs from expert demonstrations in partially observable environments.