New method improves meta-reinforcement learning efficiency.
problem Sample inefficiency in meta-reinforcement learning.
method Hindsight Foresight Relabeling (HFR) method.
result HFR improves performance on various meta-reinforcement learning tasks.
On-device research index
arXiv research
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.
168,657 papers · 148 categories
Trend · papers per month
48 results for “agent relabeling”
PEAR dynamically reconfigures agent roles to prevent persistent biases in multi-agent debates.
problem Persistent positional biases and sensitivity to role assignments in fixed topologies.
method Dynamic reconfiguration of agent roles and sparse topologies based on evolving agent states.
result Significantly improves average accuracy over debate baselines across multiple reasoning benchmarks.
Language creates a compact representation of the world and allows the description of unlimited situations and objectives through compositionality. While these characterizations may foster instructing, conditioning or structuring interactive agent behavior, it remains an open-problem to correctly relate language underst…
This work improves RL for complex robotic tasks by guiding exploration with task-specific goal distributions.
problem Solving long-horizon, complex sequential tasks in robotics with sparse rewards.
method Extends hindsight relabelling to task-specific goal distributions using a small set of demonstrations.
result Significantly higher overall performance on complex robotic manipulation tasks.
Algorithm learns new tasks efficiently from past experience.
problem Lack of robustness to distributional shift in meta-reinforcement learning.
method Model Identification and Experience Relabeling (MIER) using dynamics models.
result Efficient extrapolation to out-of-distribution tasks.
Multi-task reinforcement learning (RL) aims to simultaneously learn policies for solving many tasks. Several prior works have found that relabeling past experience with different reward functions can improve sample efficiency. Relabeling methods typically ask: if, in hindsight, we assume that our experience was optimal…
Identifies minimal training subset to flip a prediction.
problem Flipping predictions in machine learning models.
method Extended influence function for relabeling minimal subset.
result Relabeling fewer than 2% of training points can flip a prediction.
Cincer cleans both new and past data by identifying and relabeling suspicious and counter-examples.
problem Sequential learning under label noise, especially in applications with human supervision.
method Cincer uses example-based explanations to identify and relabel suspicious and counter-examples, leveraging Fisher information matrix approximation.
result Cincer achieves better data and models by clarifying the model's suspicions, especially with FIM approximation.
Paper proposes methods to improve SVM classifiers in noisy data scenarios.
problem Improving SVM classifiers when training data contains label noise.
method Mixed Integer Linear and Non Linear models with relabeling and clustering.
result Effective methods improve SVM performance in noisy data scenarios.
Sparse reward is one of the most challenging problems in reinforcement learning (RL). Hindsight Experience Replay (HER) attempts to address this issue by converting a failed experience to a successful one by relabeling the goals. Despite its effectiveness, HER has limited applicability because it lacks a compact and un…
One of the key reasons for the high sample complexity in reinforcement learning (RL) is the inability to transfer knowledge from one task to another. In standard multi-task RL settings, low-reward data collected while trying to solve one task provides little to no signal for solving that particular task and is hence ef…
For an autonomous agent to fulfill a wide range of user-specified goals at test time, it must be able to learn broadly applicable and general-purpose skill repertoires. Furthermore, to provide the requisite level of generality, these skills must handle raw sensory input such as images. In this paper, we propose an algo…
Current reinforcement learning (RL) algorithms can be brittle and difficult to use, especially when learning goal-reaching behaviors from sparse rewards. Although supervised imitation learning provides a simple and stable alternative, it requires access to demonstrations from a human supervisor. In this paper, we study…
Improved anomaly detection for launch vehicle propulsion systems using LSTM and statistical relabeling.
problem Detecting anomalies in real-time telemetry data for launch vehicles.
method Utilized LSTM networks for anomaly classification, introduced a statistical detector based on Mahalanobis distance and forward-backward detection fractions to adjust training labels.
result Precision and recall of the LSTM classifier improved by 7% and 22% respectively after statistical relabeling.
Study matches two noisy point clouds with geometric transformations and relabeling.
problem Matching two noisy point clouds with orthogonal transformations and relabeling.
method Information-theoretic results and Ping-Pong algorithm for computational alignment.
result The Ping-Pong algorithm retrieves the planted signal after one step.
Deep neural networks (DNNs) are powerful tools in computer vision tasks. However, in many realistic scenarios label noise is prevalent in the training images, and overfitting to these noisy labels can significantly harm the generalization performance of DNNs. We propose a novel technique to identify data with noisy lab…
When Daan Krammer and Stephen Bigelow independently proved that braid groups are linear, they used the Lawrence-Krammer-Bigelow representation for generic values of its variables q and t. The t variable is closely connected to the traditional Garside structure of the braid group and plays a major role in Krammer's alge…
When learning from positive and unlabelled data, it is a strong assumption that the positive observations are randomly sampled from the distribution of conditional on , where X stands for the feature and Y the label. Most existing algorithms are optimally designed under the assumption. However, for many real…
FairUDT uses uplift decision trees to detect and mitigate discrimination in training data.
problem Bias in machine learning classifiers due to historical discrimination or underrepresentation of minority groups.
method Integrates uplift modeling with decision trees and introduces a modified leaf relabeling approach for fairness.
result Achieves an acceptable accuracy-discrimination tradeoff while maintaining interpretability.
The study examines how permutation-based optimization performance varies across different function representations.
problem Understanding how the order of function evaluations affects optimization performance.
method Iterative search setting with sampling without replacement, algebraic function recombination, correlation analysis, hierarchical clustering, PCA, ANOVA.
result Algebraically modified benchmarks yield stable re-rankings and coherent clusters of functions and sampling policies, indicating non-additive search effort.
We propose Generative Well-intentioned Networks (GWINs), a novel framework for increasing the accuracy of certainty-based, closed-world classifiers. A conditional generative network recovers the distribution of observations that the classifier labels correctly with high certainty. We introduce a reject option to the cl…
Many machine learning systems rely on data collected in the wild from untrusted sources, exposing the learning algorithms to data poisoning. Attackers can inject malicious data in the training dataset to subvert the learning process, compromising the performance of the algorithm producing errors in a targeted or an ind…
Study efficient interactive learning for structured outputs with reliable computation.
problem Interactive learning with noisy labels and structured output spaces.
method Identify and utilize CRISPs (probabilistic models) that guarantee reliable and efficient computation of probabilistic quantities.
result CRISPs enable robust and efficient active and skeptical learning in large structured output spaces.
We propose new positive definite kernels for permutations. First we introduce a weighted version of the Kendall kernel, which allows to weight unequally the contributions of different item pairs in the permutations depending on their ranks. Like the Kendall kernel, we show that the weighted version is invariant to rela…
Improves k-NN for monotonic data with robustness against noise.
problem Class noise in real-life data violates monotonic constraints in k-NN.
method Monotonic Fuzzy k-NN (MonFkNN) with new fuzzy membership calculation.
result Significant accuracy improvements and robustness against monotonic noise.
We survey the role of symmetry in diffeomorphic registration of landmarks, curves, surfaces, images and higher-order data. The infinite dimensional problem of finding correspondences between objects can for a range of concrete data types be reduced resulting in compact representations of shape and spatial structure. Th…
Many popular network models rely on the assumption of (vertex) exchangeability, in which the distribution of the graph is invariant to relabelings of the vertices. However, the Aldous-Hoover theorem guarantees that these graphs are dense or empty with probability one, whereas many real-world graphs are sparse. We prese…
Autoencoding Random Forestsstat.ML
Proposes autoencoding with random forests using spectral graph theory.
problem Learning low-dimensional embeddings of random forest models.
method Combines nonparametric statistics and spectral graph theory for optimization.
result Establishes a universal consistent decoder for random forest models.
A new permutation method improves two-sample testing power.
problem Two-sample testing with improved power and validity.
method Structured block-restricted cross-swaps.
result Block-restricted permutations achieve higher power than full permutations.
Linear models can be poisoned by shifting a fraction of one class's data, revealing scaling laws and weight alignment.
problem Understanding and quantifying data poisoning in linear models.
method Analysis of ridge least squares with an unpenalized intercept, using resolvent techniques and random matrix theory.
result Closed-form limits for the poisoned score, revealing scaling laws and weight alignment with the poisoning direction.
Vakonomic Fluidsmath-ph
Novel discretization of Euler equations for incompressible fluids.
problem Nonholonomic constraints in discrete fluid dynamics.
method Vakonomic perspective on Lie group of volume-preserving diffeomorphisms.
result Discrete fluid trajectories remain geodesics on a sub-Riemannian manifold.
Deep neural networks have achieved impressive success in large-scale visual object recognition tasks with a predefined set of classes. However, recognizing objects of novel classes unseen during training still remains challenging. The problem of detecting such novel classes has been addressed in the literature, but mos…
Study investigates one-shot semi-supervised learning for image classification.
problem Training deep networks requires many labeled samples, limiting adoption.
method Empirical investigation of FixMatch method for one-shot semi-supervised learning.
result Uneven class accuracy is a barrier to high performance in one-shot semi-supervised learning.
CNNs improve transient detection in DES-SN images.
problem Automated identification of transients in astronomical images.
method Convolutional Neural Networks (CNNs) for image classification.
result CNNs achieve efficiency in identifying non-artifacts from artifacts.
A new measure of causal influence quantifies intrinsic contributions in DAGs.
problem Quantifying intrinsic causal contributions in Directed Acyclic Graphs (DAGs).
method Recursive decomposition of node contributions, structure-preserving interventions, Shapley symmetrization.
result A measure of intrinsic causal contribution that is invariant to node relabeling.
Cold posteriors improve Bayesian neural networks by reducing overestimation of aleatoric uncertainty.
problem Overestimation of aleatoric uncertainty in Bayesian neural networks.
method Tuning the temperature of the posterior on a validation set.
result Reducing temperature leads to better reflection of true prior beliefs.
Method models other agents' behaviors without requiring direct observation.
problem Understanding and interacting effectively with other agents in reinforcement learning.
method Extracts representations from local observations of the controlled agent using encoder-decoder architectures.
result The method achieves higher returns than baseline methods in multi-agent environments.
New MCMC method tackles label-switching problem for clustering.
problem Label-switching problem impedes MCMC efficiency in discrete clustering.
method Formulated optimal transport couplings for partition space.
result Our method efficiently overcomes label-switching problem.
We tackle the Multi-task Batch Reinforcement Learning problem. Given multiple datasets collected from different tasks, we train a multi-task policy to perform well in unseen tasks sampled from the same distribution. The task identities of the unseen tasks are not provided. To perform well, the policy must infer the tas…
Agent-to-Agent Finance: Blockchain Payments and Trust Infrastructure for Autonomous AI Agentsq-fin.GN
Agent-to-agent finance aims to manage payments and trust for AI agents.
problem Managing financial interactions between autonomous AI agents.
method Develops agent-to-agent finance concept and explores blockchain solutions.
result Agent-to-agent finance can address coordination frictions in financial markets.
AI agents manage portfolios, improving on human oversight.
problem Improving strategic asset allocation for institutional investors.
method 50 specialized agents produce capital market assumptions, construct portfolios, critique, and vote on each other's output.
result Meta-agent compares forecasts with realized returns and improves agent performance.
This paper aims to incorporate passive symmetries in machine learning for better generalization.
problem Machine learning's reliance on arbitrary choices leads to passive symmetries that can limit generalization.
method Translation among physics, mathematics, and machine learning to understand and implement passive symmetries.
result Respecting passive symmetries can improve machine learning's ability to generalize.
RL agents outperform baselines in asset allocation.
problem Optimizing asset allocation using reinforcement learning.
method Model-free deep RL agents trained on real-world stock prices.
result RL agents significantly outperformed random and uniform allocation.
Agents learn to give rewards to others in a shared learning environment.
problem How to encourage cooperation among RL agents in a shared environment.
method Each agent learns a reward function to influence others, optimizing for its own and others' extrinsic objectives.
result Agents significantly outperform standard RL in Markov games, often finding near-optimal division of labor.
New algorithm reduces regret in multi-agent bandits with malicious agents.
problem Collaboration between honest and malicious agents in multi-armed bandits.
method Dynamic reduction of communication with malicious agents, learning who is malicious.
result Algorithm reduces regret even with a single malicious agent, assuming is small compared to .
Regret analysis is challenging in Multi-Agent Reinforcement Learning (MARL) primarily due to the dynamical environments and the decentralized information among agents. We attempt to solve this challenge in the context of decentralized learning in multi-agent linear-quadratic (LQ) dynamical systems. We begin with a simp…
We formulate and analyze a multi-agent model for the evolution of individual and systemic risk in which the local agents interact with each other through a central agent who, in turn, is influenced by the mean field of the local agents. The central agent is stabilized by a bistable potential, the only stabilizing force…
Algorithm maximizes total reward in multi-agent bandits with adversarial corruptions.
problem Maximizing total reward in multi-agent bandits with adversarial corruptions.
method Proposes a cooperative learning algorithm robust to adversarial corruptions.
result Demonstrates an additive regret term for an adversary with unknown corruption budget.