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.
A novel Q-learning variant reduces underestimation bias in deep actor-critic methods for reinforcement learning.
Theoretical analysis improves understanding of Deep Q-Learning's behavior.
Proposes a deep spectral Q-learning for mobile health data.
EBQL reduces bias in Q-learning for improved performance.
Currently, many applications in Machine Learning are based on define new models to extract more information about data, In this case Deep Reinforcement Learning with the most common application in video games like Atari, Mario, and others causes an impact in how to computers can learning by himself with only informatio…
The breakthrough of deep Q-Learning on different types of environments revolutionized the algorithmic design of Reinforcement Learning to introduce more stable and robust algorithms, to that end many extensions to deep Q-Learning algorithm have been proposed to reduce the variance of the target values and the overestim…
Q-learning with neural network function approximation (neural Q-learning for short) is among the most prevalent deep reinforcement learning algorithms. Despite its empirical success, the non-asymptotic convergence rate of neural Q-learning remains virtually unknown. In this paper, we present a finite-time analysis of a…
PQ-learning improves Q-learning by periodically updating target estimates.
A new algorithm SRG-DQN reduces variance in deep Q-learning.
ConQUR tackles delusional bias in deep Q-learning, improving performance in Atari games.
Despite remarkable successes, Deep Reinforcement Learning (DRL) is not robust to hyperparameterization, implementation details, or small environment changes (Henderson et al. 2017, Zhang et al. 2018). Overcoming such sensitivity is key to making DRL applicable to real world problems. In this paper, we identify sensitiv…
A new algorithm for deep Q-learning with robustness to state transition uncertainty.
Deep Reinforcement Learning improves with Weighted Q-Learning to reduce bias and uncertainty.
We present a method to generate directed acyclic graphs (DAGs) using deep reinforcement learning, specifically deep Q-learning. Generating graphs with specified structures is an important and challenging task in various application fields, however most current graph generation methods produce graphs with undirected edg…
Q-learning methods represent a commonly used class of algorithms in reinforcement learning: they are generally efficient and simple, and can be combined readily with function approximators for deep reinforcement learning (RL). However, the behavior of Q-learning methods with function approximation is poorly understood,…
Paper presents a new method for Bayesian deep learning that scales to Atari games.
Recent advances in deep reinforcement learning have achieved human-level performance on a variety of real-world applications. However, the current algorithms still suffer from poor gradient estimation with excessive variance, resulting in unstable training and poor sample efficiency. In our paper, we proposed an innova…
In the past few years, off-policy reinforcement learning methods have shown promising results in their application for robot control. Deep Q-learning, however, still suffers from poor data-efficiency and is susceptible to stochasticity in the environment or reward functions which is limiting with regard to real-world a…
In this article, we sketch an algorithm that extends the Q-learning algorithms to the continuous action space domain. Our method is based on the discretization of the action space. Despite the commonly used discretization methods, our method does not increase the discretized problem dimensionality exponentially. We wil…
Kernelized Q-learning achieves good performance with minimal data.
Online random forests improve Q-learning performance in specific gym environments.
Model-free deep reinforcement learning has been shown to exhibit good performance in domains ranging from video games to simulated robotic manipulation and locomotion. However, model-free methods are known to perform poorly when the interaction time with the environment is limited, as is the case for most real-world ro…
This paper concerns automated vehicles negotiating with other vehicles, typically human driven, in crossings with the goal to find a decision algorithm by learning typical behaviors of other vehicles. The vehicle observes distance and speed of vehicles on the intersecting road and use a policy that adapts its speed alo…
Fatigue is the most vital factor of road fatalities and one manifestation of fatigue during driving is drowsiness. In this paper, we propose using deep Q-learning to analyze an electroencephalogram (EEG) dataset captured during a simulated endurance driving test. By measuring the correlation between drowsiness and driv…
New algorithms speed up inverse reinforcement learning by solving MDPs once.
Deep Q-Learning optimizes market making by balancing price risk and spread profits.
Tabular Q-learning outperforms advanced RL methods in monetary policy.
Stochastic Q-learning tackles large action spaces with reduced computation.
A Deep Q-Learning framework tackles market-making by incorporating closing auctions.
Paper addresses underestimation bias in double Q-learning, proposing a method to improve learning performance.
Study Whittle index learning algorithms for restless bandits with constant stepsizes.
We present a novel algorithm to train a deep Q-learning agent using natural-gradient techniques. We compare the original deep Q-network (DQN) algorithm to its natural-gradient counterpart, which we refer to as NGDQN, on a collection of classic control domains. Without employing target networks, NGDQN significantly outp…
A new Q-learning variant reduces underestimation bias in deep reinforcement learning.
This paper describes an improvement in Deep Q-learning called Reverse Experience Replay (also RER) that solves the problem of sparse rewards and helps to deal with reward maximizing tasks by sampling transitions successively in reverse order. On tasks with enough experience for training and enough Experience Replay mem…
We introduce a novel Deep Reinforcement Learning (DRL) algorithm called Deep Quality-Value (DQV) Learning. DQV uses temporal-difference learning to train a Value neural network and uses this network for training a second Quality-value network that learns to estimate state-action values. We first test DQV's update rules…
The paper formalizes and analyzes multi-agent Q-learning with value factorization.
We present a new algorithm that significantly improves the efficiency of exploration for deep Q-learning agents in dialogue systems. Our agents explore via Thompson sampling, drawing Monte Carlo samples from a Bayes-by-Backprop neural network. Our algorithm learns much faster than common exploration strategies such as …
Q()-Learning improves Q-Learning by separating action-value functions into different time scales.
Deep reinforcement learning finds optimal learning policies for adaptive systems.
Deep Q-Learning models optimal exercise strategies for option-type products.
In this paper, we consider same-day delivery with vehicles and drones. Customers make delivery requests over the course of the day, and the dispatcher dynamically dispatches vehicles and drones to deliver the goods to customers before their delivery deadline. Vehicles can deliver multiple packages in one route but trav…
CQL learns conservative Q-functions to improve offline RL performance.
The use of target networks has been a popular and key component of recent deep Q-learning algorithms for reinforcement learning, yet little is known from the theory side. In this work, we introduce a new family of target-based temporal difference (TD) learning algorithms and provide theoretical analysis on their conver…
Deep reinforcement learning techniques have demonstrated superior performance in a wide variety of environments. As improvements in training algorithms continue at a brisk pace, theoretical or empirical studies on understanding what these networks seem to learn, are far behind. In this paper we propose an interpretable…
Paper proposes operator deep Q-learning for quick reward adaptation.
RL agent learns to place limit orders for trading signals in financial markets.
Study shows DQN's performance degrades with temporal dependence in data.
Temporal-difference and Q-learning learn feature representations that converge to optimal ones.