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.
HydaLearn dynamically adjusts task weights for better MTL performance.
UCB-TQL learns from multiple tasks with shared dynamics and adapts to task-specific variations.
The aim of multi-task reinforcement learning is two-fold: (1) efficiently learn by training against multiple tasks and (2) quickly adapt, using limited samples, to a variety of new tasks. In this work, the tasks correspond to reward functions for environments with the same (or similar) dynamical models. We propose to l…
Meta-Dynamic models learn shared neural dynamics across tasks.
Current reinforcement learning (RL) methods can successfully learn single tasks but often generalize poorly to modest perturbations in task domain or training procedure. In this work, we present a decoupled learning strategy for RL that creates a shared representation space where knowledge can be robustly transferred. …
We propose a novel framework for multi-task reinforcement learning (MTRL). Using a variational inference formulation, we learn policies that generalize across both changing dynamics and goals. The resulting policies are parametrized by shared parameters that allow for transfer between different dynamics and goal condit…
This paper tackles online reinforcement learning for unseen tasks with unknown boundaries.
Develops CLDS models to model neural activity with nonlinear dynamics.
A method for learning a context latent vector to improve generalization in model-based RL.
RNNs compute by warping neural representations over time.
New method learns adaptive exploration strategies for dynamic tasks.
Enhances load forecasting for multiple entities with dynamic similarities.
Study task-guided exploration in linear dynamical systems, improving sample complexity.
Trained recurrent networks are powerful tools for modeling dynamic neural computations. We present a target-based method for modifying the full connectivity matrix of a recurrent network to train it to perform tasks involving temporally complex input/output transformations. The method introduces a second network during…
Paper proposes a method to make learned models focus on task-relevant information.
In dynamic environments, learned controllers are supposed to take motion into account when selecting the action to be taken. However, in existing reinforcement learning works motion is rarely treated explicitly; it is rather assumed that the controller learns the necessary motion representation from temporal stacks of …
TempLe learns transition templates for efficient multi-task RL.
Dynamic functional connectivity (FC) has in recent years become a topic of interest in the neuroimaging community. Several models and methods exist for both functional magnetic resonance imaging (fMRI) and electroencephalography (EEG), and the results point towards the conclusion that FC exhibits dynamic changes. The e…
Planning has been very successful for control tasks with known environment dynamics. To leverage planning in unknown environments, the agent needs to learn the dynamics from interactions with the world. However, learning dynamics models that are accurate enough for planning has been a long-standing challenge, especiall…
In sequence generation task, many works use policy gradient for model optimization to tackle the intractable backpropagation issue when maximizing the non-differentiable evaluation metrics or fooling the discriminator in adversarial learning. In this paper, we replace policy gradient with proximal policy optimization (…
This work uses reinforcement learning to optimize task scheduling and execution in a dynamic multi-agent warehouse environment.
Study on multi-head softmax attention dynamics for in-context learning.
While model-based deep reinforcement learning (RL) holds great promise for sample efficiency and generalization, learning an accurate dynamics model is often challenging and requires substantial interaction with the environment. A wide variety of domains have dynamics that share common foundations like the laws of clas…
Reinforcement learning requires manual specification of a reward function to learn a task. While in principle this reward function only needs to specify the task goal, in practice reinforcement learning can be very time-consuming or even infeasible unless the reward function is shaped so as to provide a smooth gradient…
We compute the transition probability between two learning tasks, and show that it decomposes into two factors. The first depends on the geometry of the loss landscape of a model trained on each task, independent of any particular model used. This is related to an information theoretic distance function, but is insuffi…
Transformer model for probabilistic dynamical systems.
Multi-task learning is a method for improving the generalizability of multiple tasks. In order to perform multiple classification tasks with one neural network model, the losses of each task should be combined. Previous studies have mostly focused on multiple prediction tasks using joint loss with static weights for tr…
RL agents learn from a few tasks to generalize to new ones.
Learning robot tasks or controllers using deep reinforcement learning has been proven effective in simulations. Learning in simulation has several advantages. For example, one can fully control the simulated environment, including halting motions while performing computations. Another advantage when robots are involved…
New method for online meta-learning reduces dynamic regret in changing environments.
Approximate dynamic programming algorithms, such as approximate value iteration, have been successfully applied to many complex reinforcement learning tasks, and a better approximate dynamic programming algorithm is expected to further extend the applicability of reinforcement learning to various tasks. In this paper w…
RNNs classify text by accumulating evidence on a low-dimensional manifold.
Examines multiagent systems for complex learning tasks.
Study on how optimal representations emerge during deep learning training, focusing on the role of implicit regularization.
GD-VAEs learn dynamics from observations using geometric and topological information.
Solving goal-oriented tasks is an important but challenging problem in reinforcement learning (RL). For such tasks, the rewards are often sparse, making it difficult to learn a policy effectively. To tackle this difficulty, we propose a new approach called Policy Continuation with Hindsight Inverse Dynamics (PCHID). Th…
Dynamical system models (including RNNs) often lack the ability to adapt the sequence generation or prediction to a given context, limiting their real-world application. In this paper we show that hierarchical multi-task dynamical systems (MTDSs) provide direct user control over sequence generation, via use of a latent…
Researchers analyze how RNNs solve intent detection tasks using dynamical systems theory.
In this work, dynamic Bayesian multinets are introduced where a Markov chain state at time t determines conditional independence patterns between random variables lying within a local time window surrounding t. It is shown how information-theoretic criterion functions can be used to induce sparse, discriminative, and c…
Paper analyzes AI's impact on job tasks, predicting future demands.
New algorithms improve multi-task learning across different environments.
Real-life control tasks involve matters of various substances---rigid or soft bodies, liquid, gas---each with distinct physical behaviors. This poses challenges to traditional rigid-body physics engines. Particle-based simulators have been developed to model the dynamics of these complex scenes; however, relying on app…
New attention mechanism improves meta-transfer learning in dynamic tasks.
Proposes HOTA-FedGradNorm for faster and robust PFL in noisy channels.
HySRL improves RL sample efficiency with shifted-dynamics data.
Understanding the functional architecture of the brain in terms of networks is becoming increasingly common. In most fMRI applications functional networks are assumed to be stationary, resulting in a single network estimated for the entire time course. However recent results suggest that the connectivity between brain …
Broker uses multi-task dynamic pricing to learn competitive prices in credit markets.
VFDS selects dynamic features for efficient HAR tasks, optimizing performance-cost trade-offs.