Behavior Transfer improves reinforcement learning by leveraging pre-trained policies.
problem Efficient transfer of knowledge in reinforcement learning.
method Behavior Transfer (BT) that uses pre-trained policies for exploration.
result BT combined with pre-training leads to better solutions than without pre-training.
Model assesses credit risk using behavioral data from Experian and Bank of Italy.
problem Improving credit risk assessment in financial institutions.
method Statistical and machine learning techniques applied to behavioral data from Experian and Bank of Italy.
result Demonstrates transferability of the model from private to central data.
As reinforcement learning agents are tasked with solving more challenging and diverse tasks, the ability to incorporate prior knowledge into the learning system and to exploit reusable structure in solution space is likely to become increasingly important. The KL-regularized expected reward objective constitutes one po…
Modern software systems provide many configuration options which significantly influence their non-functional properties. To understand and predict the effect of configuration options, several sampling and learning strategies have been proposed, albeit often with significant cost to cover the highly dimensional configu…
Learning transferable knowledge across similar but different settings is a fundamental component of generalized intelligence. In this paper, we approach the transfer learning challenge from a causal theory perspective. Our agent is endowed with two basic yet general theories for transfer learning: (i) a task shares a c…
A major bottleneck for developing general reinforcement learning agents is determining rewards that will yield desirable behaviors under various circumstances. We introduce a general mechanism for automatically specifying meaningful behaviors from raw pixels. In particular, we train a generative adversarial network to …
Hierarchical decoupling improves sample efficiency for complex robots.
problem Learning long-range behaviors on complex robots.
method Two-part policy: low-level imitation and high-level transfer, with KL regularization.
result Hierarchical transfer significantly improves zero-shot high-level transfer and stabilizes learning.
Granger causality is a fundamental technique for causal inference in time series data, commonly used in the social and biological sciences. Typical operationalizations of Granger causality make a strong assumption that every time point of the effect time series is influenced by a combination of other time series with a…
Modeling student behaviors and multiple predictions for early intervention.
problem Predicting student outcomes and interactions among multiple tasks.
method Proposes a variant of LSTM and soft-attention mechanism for heterogeneous behaviors, and co-attention mechanism for task interactions.
result Demonstrated effectiveness in predicting student outcomes and interactions.
Transfer learning improves dynamic model transfer for soft robotic hands.
problem Improving dynamic model transfer for underactuated soft robotic hands.
method Derive an upper bound on the Lyapunov exponent and use it to improve transfer.
result Significant improvement over traditional fine-tuning methods.
We present an agent behavior based microscopic model that induces jumps, spikes and high volatility phases in the price process of a traded asset. We transfer dynamics of thermally activated jumps of an unexcited/ excited two state system discussed in the context of quantum mechanics to agent socio-economic behavior an…
This paper explores how the generalization of substitute classifiers affects the success of black-box adversarial attacks.
problem Understanding the factors driving the transferability of black-box adversarial examples.
method Max-min adversarial example game framework and theoretical generalization bounds.
result Substitute NN with better generalization behavior results in more transferable adversarial examples.
In a Massive Open Online Course (MOOC), predictive models of student behavior can support multiple aspects of learning, including instructor feedback and timely intervention. Ongoing courses, when the student outcomes are yet unknown, must rely on models trained from the historical data of previously offered courses. I…
FRA-Attack improves adversarial transferability for closed-source MLLMs by aligning visual focus across models.
problem Improving adversarial transferability for closed-source MLLMs, especially with high accuracy.
method Unified frequency-domain regularization approach: high-pass DCT objective for feature alignment and Frequency-domain Gradient Regularization (FGR) for gradient optimization.
result FRA-Attack achieves superior cross-model transferability, especially on GPT-5.4, Claude-Opus-4.6, and Gemini-3-flash.
Transfer learning improves causal model estimates in small samples.
problem Challenges in estimating individual treatment effects (ITE) from small datasets.
method Treatment Agnostic Representation Networks (TARNet) with transfer learning (TL-TARNet).
result Transfer learning reduces ITE error and bias in small samples.
Transfer learning improves prediction quality in high-dimensional sparse regression.
problem Selecting hyperparameters for Lasso-based transfer learning algorithms.
method Asymptotic analysis using the replica method.
result Ignoring one type of transferred information has minimal impact on performance.
New method creates powerful, transferable adversarial attacks for deep learning networks.
problem Vulnerability of deep learning networks to adversarial attacks.
method Developed a method to generate strong, transferable adversarial attacks.
result Demonstrated that the proposed method can easily transfer strong adversarial attacks between different models.
This paper extends transfer operator theory to McKean-Vlasov equations.
problem Analyzing the behavior of complex dynamical systems using transfer operators.
method Extended dynamic mode decomposition and Galerkin projection.
result Finite-dimensional approximations of transfer operators computed.
The composition of elementary behaviors to solve challenging transfer learning problems is one of the key elements in building intelligent machines. To date, there has been plenty of work on learning task-specific policies or skills but almost no focus on composing necessary, task-agnostic skills to find a solution to …
Integrates skills and world models for efficient task solving and transfer.
problem Quickly solve new tasks in complex environments using reusable knowledge.
method Leverages partial amortization for fast adaptation and online skill planning.
result Improved sample efficiency in single tasks and transfer between tasks.
New approach transfers rewards learned in one environment to reinforcement learning in a new environment.
problem Transfer of rewards learned using inverse reinforcement learning from one environment to a new, different environment.
method Formulate the problem as a joint system of Bellman equations, develop minimax estimators for the target soft-q-function, solve the source and target system of equations jointly. result The coupled approach removes the first-order influence of source Bellman residual error compared to the sequential approach.
Computer simulation provides an automatic and safe way for training robotic control policies to achieve complex tasks such as locomotion. However, a policy trained in simulation usually does not transfer directly to the real hardware due to the differences between the two environments. Transfer learning using domain ra…
This paper tackles online strategic decision making with asymmetry and knowledge transportability.
problem Strategic decision making with information asymmetry and knowledge transportability challenges.
method Developed a sample-efficient algorithm for online learning under these conditions.
result Proved sample complexity of O(1/ε2) for learning an ε-optimal policy. New bounds for linear interpolators show how they generalize under covariate shifts.
problem Understanding how linear interpolators generalize under covariate shifts.
method Proved non-asymptotic excess risk bounds for benignly-overfit linear interpolators in transfer learning.
result Identified beneficial and malignant covariate shifts based on overparameterization degree.
Proposes TFCL to mitigate negative transfer in MTL by collaborating across features and tasks.
problem Negative transfer in Multi-Task Learning (MTL) due to dissimilar tasks.
method Task-Feature Collaborative Learning (TFCL) with heterogeneous block-diagonal structure regularizer and optimization method.
result Global convergence and block-diagonal structure recovery guarantees.
MuJAM learns traffic signal control policies that generalize to unseen intersections and traffic conditions.
problem Lack of transferability in reinforcement learning methods for traffic signal control.
method Model-based graph reinforcement learning with explicit coordination and generalization to both cyclic and acyclic constraints.
result MuJAM outperforms existing methods in zero-shot and larger transfer settings.
Robust data fusion via subsampling improves model performance for rare data types.
problem Challenges in integrating large, contaminated external data with limited target data.
method Subsampling strategies to reduce biases and minimize variances, combined with error bounds analysis.
result Proposed methods enhance transfer learning performance, especially for rare data types.
ActiLabel learns activity patterns across diverse sensor devices.
problem Limited adoption of activity recognition models across different domains due to diverse sensor devices.
method Combination of graph model and optimal tiered mapping for learning activity labels.
result Superior performance compared to state-of-the-art methods on public datasets.
RaNNDy uses randomized neural networks to learn transfer operators efficiently.
problem Efficiently learning transfer operators from data.
method Randomized neural network approach with randomly initialized hidden layers and trained output layer.
result Significant reduction in training time and resources with improved stability.
This study examines how the size and alignment of pretraining data affect the performance of large language models on downstream tasks.
problem Understanding how the size and alignment of pretraining data impact the performance of large language models on downstream tasks.
method Investigated the scaling behavior of large language models in a transfer learning setting, focusing on machine translation tasks.
result The size of the finetuning dataset and the distribution alignment between pretraining and downstream data significantly influence the scaling behavior of downstream performance.
New method saves computational budget by ranking and transferring learning curves.
problem Expensive automated machine learning methods for hyperparameter and neural architecture optimization.
method Tackles as a ranking and transfer learning problem, optimizing a pairwise ranking loss and leveraging learning curves from other datasets.
result Accelerates neural architecture search by a factor of up to 100 without significant performance degradation.
Evaluates transfer learning methods in dynamic data availability scenarios.
problem Real-world data availability varies over time, leading to unrealistic TL method evaluations.
method Proposes a data manipulation framework to simulate varying data availability and domain transformations.
result Demonstrates the usefulness of the framework on proprietary and publicly available datasets.
Improves imitation learning in RL by learning reward function efficiently.
problem Lack of effective reward function approximation in AIRL for imitation tasks.
method Proposes Off-Policy AIRL that combines adversarial learning with efficient reward function approximation.
result Shows superior imitation performance and efficiency compared to state-of-the-art AIL algorithms.
Study shows how to motivate AI agents like humans through learning from demonstrations.
problem Transfer human-like intrinsic motivation to AI agents in RL.
method Inverse RL approach to learn an exploration bonus from demonstrations.
result AI agents can learn and use complex exploration behaviors from demonstrations.
Unified framework for analyzing graph neural operators converging to graph limits.
problem Analyzing convergence of graph neural operators to graph limits.
method Develops a unified spectral framework for graph neural operators under various graphon assumptions.
result Unified framework enables direct comparison of convergence rates and tradeoffs.
Unified framework predicts S&P500 index direction using transfer learning and causal graph.
problem Predicting the movement of financial indices like S&P500.
method Transfer learning, causal graph, multidisciplinary knowledge, VAE network.
result 74.3% accuracy, 67% F1-score, 0.42 Matthew correlation on 12 years test period.
New algorithm reduces sample complexity for new tasks by leveraging prior knowledge.
problem Designing reinforcement learning agents that reduce sample complexity for new tasks.
method Designing an algorithm that quickly identifies an accurate solution by seeking informative state-action pairs from related tasks, using a generative model.
result PAC bounds on sample complexity demonstrate the benefits of using prior knowledge.
Study models human investors' sub-rational behavior in financial markets.
problem Lack of a comprehensive model for human sub-rationality in financial markets.
method Flexible reinforcement learning model incorporating five human sub-rational aspects.
result Model accurately reproduces human behavior and reveals insights into market dynamics.
Quantifying behavior is crucial for many applications in neuroscience. Videography provides easy methods for the observation and recording of animal behavior in diverse settings, yet extracting particular aspects of a behavior for further analysis can be highly time consuming. In motor control studies, humans or other …
We develop DTs for PDE models using KL-NN and TL, analyzing TL's moment equations and one-shot learning for exactness.
problem Creating accurate digital twins for systems governed by PDEs under changing conditions.
method We use KL-NN surrogate models and transfer learning to construct DTs, analyzing the moment equations and proposing one-shot and few-shot learning methods.
result For linear PDEs, one-shot TL is exact; for nonlinear PDEs, some parameters can be transferred with minimal error.
Agents learn social skills from each other, improving performance.
problem Independent RL agents fail to use social learning.
method Imposed constraints, model-based auxiliary loss, mixed training.
result Agents trained with social learning outperform solo-trained agents.
Generalized Hindsight improves RL by reusing data from one task for another.
problem High sample complexity in reinforcement learning due to wasted uninformative data.
method Approximate inverse reinforcement learning to relabel behaviors with better-suited tasks.
result Efficient reuse of samples, reducing sample complexity on multi-task RL tasks.
We seek to align agent behavior with a user's objectives in a reinforcement learning setting with unknown dynamics, an unknown reward function, and unknown unsafe states. The user knows the rewards and unsafe states, but querying the user is expensive. To address this challenge, we propose an algorithm that safely and …
Future robots should follow human social norms in order to be useful and accepted in human society. In this paper, we leverage already existing social knowledge in human societies by capturing it in our framework through the notion of social norms. We show how norms can be used to guide a reinforcement learning agent t…
The paper studies practical estimation and interpretation of Rényi transfer entropy.
problem Challenges in accurately estimating and interpreting Rényi transfer entropy.
method Systematic study of k-nearest neighbor estimator for Rényi entropy and transfer entropy.
result Effective estimates of effective Rényi transfer entropy can accurately capture directional information flow.
A new method learns from multi-modal sequences with external memory.
problem Learning new modes in a dynamic environment without prior knowledge.
method Maintains a neural episodic memory with a Dirichlet Process prior to store mode descriptors and transfers knowledge through retrieval.
result Performs continual learning favorably compared to mainstream approaches.
Physics-based framework improves building energy forecasting.
problem Lack of physical correspondence in machine learning models for building energy systems.
method Combines LTI SSMs with subspace-based domain adaptation (SDA).
result Physics-derived subspaces align with data-derived subspaces for better forecasting.
Smartwatches are increasingly being used to recognize human daily life activities. These devices may employ different kind of machine learning (ML) solutions. One of such ML models is Gradient Boosting Machine (GBM) which has shown an excellent performance in the literature. The GBM can be trained on available data set…