A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Graph neural network executes value iteration for flexible environments.
Learning in a non-stationary environment is an inevitable problem when applying machine learning algorithm to real world environment. Learning new tasks without forgetting the previous knowledge is a challenge issue in machine learning. We propose a Kalman Filter based modifier to maintain the performance of Neural Net…
GIB improves neural network generalization by dynamically selecting task-relevant features across different sequential environments.
In this paper, we train a recurrent neural network to learn dynamics of a chaotic road environment and to project the future of the environment on an image. Future projection can be used to anticipate an unseen environment for example, in autonomous driving. Road environment is highly dynamic and complex due to the int…
PPOPT uses pretraining to speed up reinforcement learning in physics simulations.
Recurrent networks learn beliefs from history in partially observable environments.
Deep Recurrent Q-Network improves autonomous driving in urban areas with pedestrians.
A new neural network model improves reinforcement learning efficiency.
This work develops agents to learn generalizable policies for dynamic network environments.
A generative recurrent neural network is quickly trained in an unsupervised manner to model popular reinforcement learning environments through compressed spatio-temporal representations. The world model's extracted features are fed into compact and simple policies trained by evolution, achieving state of the art resul…
In Business Intelligence, accurate predictive modeling is the key for providing adaptive decisions. We studied predictive modeling problems in this research which was motivated by real-world cases that Microsoft data scientists encountered while dealing with e-commerce transaction fraud control decisions using transact…
Reinforcement learning is concerned with identifying reward-maximizing behaviour policies in environments that are initially unknown. State-of-the-art reinforcement learning approaches, such as deep Q-networks, are model-free and learn to act effectively across a wide range of environments such as Atari games, but requ…
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…
Meta-learning improves drone trajectory design for dynamic wireless networks.
Although various linear log-distance path loss models have been developed, advanced models are requiring to more accurately and flexibly represent the path loss for complex environments such as the urban area. This letter proposes an artificial neural network (ANN) based multi-dimensional regression framework for path …
Predicting movement of objects while the action of learning agent interacts with the dynamics of the scene still remains a key challenge in robotics. We propose a multi-layer Long Short Term Memory (LSTM) autoendocer network that predicts future frames for a robot navigating in a dynamic environment with moving obstacl…
Bayesian segmentation and uncertainty estimation improve 3D model accuracy for factory planning.
Enhances graph neural networks by creating virtual data examples.
Paper tackles noise-robust domain adaptation in noisy environments.
Framework tackles OOD challenges in molecule property prediction by modeling environments.
Paper uses deep reinforcement learning for network slicing and traffic prediction.
FEPS models agents to learn and act in complex environments without deep neural networks.
Deep reinforcement learning (RL) has been successfully applied to a variety of game-like environments. However, the application of deep RL to visual navigation with realistic environments is a challenging task. We propose a novel learning architecture capable of navigating an agent, e.g. a mobile robot, to a target giv…
This work investigates how a naive agent can acquire its own body image in a self-supervised way, based on the predictability of its sensorimotor experience. Our working hypothesis is that, due to its temporal stability, an agent's body produces more consistent sensory experiences than the environment, which exhibits a…
Assisted by neural networks, reinforcement learning agents have been able to solve increasingly complex tasks over the last years. The simulation environment in which the agents interact is an essential component in any reinforcement learning problem. The environment simulates the dynamics of the agents' world and henc…
FAVANO improves federated learning for resource-constrained environments.
Generative Flow Networks solve shortest path problems in graphs.
XRM discovers environments without human annotations for OOD methods.
LEADS improves model generalization across different environments.
Models that can simulate how environments change in response to actions can be used by agents to plan and act efficiently. We improve on previous environment simulators from high-dimensional pixel observations by introducing recurrent neural networks that are able to make temporally and spatially coherent predictions f…
This research introduces an autonomous robot navigation method using reinforcement learning.
Neural networks struggle with extrapolation, but a new framework allows them to learn counterfactual invariances.
Dyna-style reinforcement learning is a powerful approach for problems where not much real data is available. The main idea is to supplement real trajectories, or sequences of sampled states over time, with simulated ones sampled from a learned model of the environment. However, in large state spaces, the problem of lea…
Autonomous robots need to interact with unknown, unstructured and changing environments, constantly facing novel challenges. Therefore, continuous online adaptation for lifelong-learning and the need of sample-efficient mechanisms to adapt to changes in the environment, the constraints, the tasks, or the robot itself a…
Autoencoder neural networks reconstruct missing indoor environment data.
Equivariant CNNs improve RL performance in symmetric environments.
New algorithm guarantees domain generalization with few environments.
NetHack Learning Environment (NLE) tests RL algorithms, offering scalable, complex, and challenging gameplay.
Fast and efficient motion planning algorithms are crucial for many state-of-the-art robotics applications such as self-driving cars. Existing motion planning methods become ineffective as their computational complexity increases exponentially with the dimensionality of the motion planning problem. To address this issue…
A new memory system handles non-stationary environments by self-sizing and retaining memories.
Fractal neural networks play SimCity and Conway's Game of Life on varying scales.
FAIR-NN finds invariant variables for causal inference across diverse environments.
We propose Deep Q-Networks (DQN) with model-based exploration, an algorithm combining both model-free and model-based approaches that explores better and learns environments with sparse rewards more efficiently. DQN is a general-purpose, model-free algorithm and has been proven to perform well in a variety of tasks inc…
Asynchronous Advantage Actor Critic (A3C) is an effective Reinforcement Learning (RL) algorithm for a wide range of tasks, such as Atari games and robot control. The agent learns policies and value function through trial-and-error interactions with the environment until converging to an optimal policy. Robustness and s…
Reinforcement Learning (RL) is a research area that has blossomed tremendously in recent years and has shown remarkable potential for artificial intelligence based opponents in computer games. This success is primarily due to vast capabilities of Convolutional Neural Networks (ConvNet), enabling algorithms to extract u…
Paper proposes a hybrid model for financial time series prediction using sentiment analysis.
Model-based reinforcement learning (MBRL) with model-predictive control or online planning has shown great potential for locomotion control tasks in terms of both sample efficiency and asymptotic performance. Despite their initial successes, the existing planning methods search from candidate sequences randomly generat…
Federated multi-mini-batch improves efficiency in non-IID environments.