arXiv research

New algorithms for model selection in off-policy evaluation of reinforcement learning.

A new feature selection method using random forest and Kolmogorov filter.

A new method selects a representative subsample for efficient kernel density estimation.

ACS is an interactive framework for model-free selection with guaranteed error control.

A new method selects representative subdata without assuming underlying models.

Proposes HSIC-Lasso for selective inference in non-linear data.

Forecasting a time series from multivariate predictors constitutes a challenging problem, especially using model-free approaches. Most techniques, such as nearest-neighbor prediction, quickly suffer from the curse of dimensionality and overfitting for more than a few predictors which has limited their application mostl…

Paper proposes a privacy-preserving knockoff inference method.

A new model-free subsampling method using uniform designs is proposed.

This research evaluates learning models for bionic robots, focusing on transfer function identification.

Variable selection is of significant importance for classification and regression tasks in machine learning and statistical applications where both predictability and explainability are needed. In this paper, a Copula Entropy (CE) based method for variable selection which use CE based ranks to select variables is propo…

The combined algorithm selection and hyperparameter tuning (CASH) problem is characterized by large hierarchical hyperparameter spaces. Model-free hyperparameter tuning methods can explore such large spaces efficiently since they are highly parallelizable across multiple machines. When no prior knowledge or meta-data e…

Combines model-based and model-free RL for better financial market performance.

Feature selection is central to contemporary high-dimensional data analysis. Grouping structure among features arises naturally in various scientific problems. Many methods have been proposed to incorporate the grouping structure information into feature selection. However, these methods are normally restricted to a li…

Unified framework for policy improvement in RL with benefits in data efficiency and computation.

The paper proposes a method to estimate latent structures in multivariate data without assuming their existence.

Paper tackles action selection in deep RL, proposing a data-driven approach.

Study compares model-free valuation to actual financial outcomes, finds it slightly conservative.

We introduce Dynamic Planning Networks (DPN), a novel architecture for deep reinforcement learning, that combines model-based and model-free aspects for online planning. Our architecture learns to dynamically construct plans using a learned state-transition model by selecting and traversing between simulated states and…

Discovering and exploiting the causal structure in the environment is a crucial challenge for intelligent agents. Here we explore whether causal reasoning can emerge via meta-reinforcement learning. We train a recurrent network with model-free reinforcement learning to solve a range of problems that each contain causal…

A new method stabilizes deep reinforcement learning by using QGraphs to retain replay memory information.

New model-free DR-RL algorithm with finite sample complexity.

We prove the existence and uniqueness of solutions of SDEs with Lipschitz coefficients, driven by continuous, model-free martingales. The main tool in our reasoning is Picard's iterative procedure and a model-free version of the Burkholder-Davis-Gundy inequality for integrals driven by model-free, continuous martingale…

Soft Actor-Critic is a state-of-the-art reinforcement learning algorithm for continuous action settings that is not applicable to discrete action settings. Many important settings involve discrete actions, however, and so here we derive an alternative version of the Soft Actor-Critic algorithm that is applicable to dis…

We develop a simple and computationally efficient significance test for the features of a machine learning model. Our forward-selection approach applies to any model specification, learning task and variable type. The test is non-asymptotic, straightforward to implement, and does not require model refitting. It identif…

Safe RL-based vibration control using LQR guidance.

Federated Q-Learning achieves linear regret speedup with low communication cost.

Unified reinforcement learning methods using hybrid inference.

A new model-free algorithm achieves near-optimal regret for infinite-horizon MDPs.

New model-free algorithm achieves similar LQR regret guarantees.

FORK improves model-free reinforcement learning performance.

New RL algorithm achieves sublinear regret and constraint violation without simulators.

Model-free reinforcement learning is known to be memory and computation efficient and more amendable to large scale problems. In this paper, two model-free algorithms are introduced for learning infinite-horizon average-reward Markov Decision Processes (MDPs). The first algorithm reduces the problem to the discounted-r…

The validity of the Efficient Market Hypothesis has been under severe scrutiny since several decades. However, the evidence against it is not conclusive. Artificial Neural Networks provide a model-free means to analize the prediction power of past returns on current returns. This chapter analizes the predictability in …

Ensemble learning is a very prevalent method employed in machine learning. The relative success of ensemble methods is attributed to their ability to tackle a wide range of instances and complex problems that require different low-level approaches. However, ensemble methods are relatively less popular in reinforcement …

Efficient exploration for automatic subgoal discovery is a challenging problem in Hierarchical Reinforcement Learning (HRL). In this paper, we show that intrinsic motivation learning increases the efficiency of exploration, leading to successful subgoal discovery. We introduce a model-free subgoal discovery method base…

New hybrid RL algorithm outperforms model-free and model-based methods.

Simple object representations improve model-free RL performance.

DeepFS uses deep neural networks to select significant features in ultra high-dimensional data.

Develops model-free methods for event history analysis and efficient covariate adjustment.

Policy-gradient method controls multiple non-cohesive targets.

New algorithm borrows future randomness to stabilize model-free control.

Two novel methods identify influential features in CMABs for better reward distribution.

Improved model-free RL algorithm with reduced sample complexity.

We study an exploration method for model-free RL that generalizes the counter-based exploration bonus methods and takes into account long term exploratory value of actions rather than a single step look-ahead. We propose a model-free RL method that modifies Delayed Q-learning and utilizes the long-term exploration bonu…

Improves sample efficiency in RL by matching model-based gradients.

The goal of feature selection is to identify important features that are relevant to explain an outcome variable. Most of the work in this domain has focused on identifying globally relevant features, which are features that are related to the outcome using evidence across the entire dataset. We study a more fine-grain…

We improve current instability-based methods for the selection of the number of clusters $k$ in cluster analysis by developing a normalized cluster instability measure that corrects for the distribution of cluster sizes, a previously unaccounted driver of cluster instability. We show that our normalized instability mea…