Related papers: Decorrelated Double Q-learning
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…
Overestimation is a fundamental characteristic of model-free reinforcement learning (MF-RL), arising from the principles of temporal difference learning and the approximation of the Q-function. To address this challenge, we propose a novel…
Neural networks allow Q-learning reinforcement learning agents such as deep Q-networks (DQN) to approximate complex mappings from state spaces to value functions. However, this also brings drawbacks when compared to other function…
Though deep reinforcement learning (DRL) has obtained substantial success, it may encounter catastrophic failures due to the intrinsic uncertainty of both transition and observation. Most of the existing methods for safe reinforcement…
Motivated by value function estimation in reinforcement learning, we study statistical linear inverse problems, i.e., problems where the coefficients of a linear system to be solved are observed in noise. We consider penalized estimators,…
In traditional reinforcement learning, an agent maximizes the reward collected during its interaction with the environment by approximating the optimal policy through the estimation of value functions. Typically, given a state s and action…
Deep reinforcement learning models are vulnerable to adversarial attacks that can decrease a victim's cumulative expected reward by manipulating the victim's observations. Despite the efficiency of previous optimization-based methods for…
This work considers two distinct settings: imitation learning and goal-conditioned reinforcement learning. In either case, effective solutions require the agent to reliably reach a specified state (a goal), or set of states (a…
The state of the art for model predictive control (MPC)-based distributed Q-learning is limited to first-order gradient updates of the MPC parameterization. In general, using secondorder information can significantly improve the speed of…
In many real world applications, reinforcement learning agents have to optimize multiple objectives while following certain rules or satisfying a list of constraints. Classical methods based on reward shaping, i.e. a weighted combination of…
Deep reinforcement learning (RL) algorithms can learn complex policies to optimize agent operation over time. RL algorithms have shown promising results in solving complicated problems in recent years. However, their application on…
One common approach to solve multi-objective reinforcement learning (MORL) problems is to extend conventional Q-learning by using vector Q-values in combination with a utility function. However issues can arise with this approach in the…
Reinforcement Learning (RL) consists of designing agents that make intelligent decisions without human supervision. When used alongside function approximators such as Neural Networks (NNs), RL is capable of solving extremely complex…
Reinforcement learning in discrete-continuous hybrid action spaces presents fundamental challenges for robotic manipulation, where high-level task decisions and low-level joint-space execution must be jointly optimized. Existing approaches…
Deep Q-Networks algorithm (DQN) was the first reinforcement learning algorithm using deep neural network to successfully surpass human level performance in a number of Atari learning environments. However, divergent and unstable behaviour…
The ensemble method is a promising way to mitigate the overestimation issue in Q-learning, where multiple function approximators are used to estimate the action values. It is known that the estimation bias hinges heavily on the ensemble…
We present a coarse-to-fine discretisation method that enables the use of discrete reinforcement learning approaches in place of unstable and data-inefficient actor-critic methods in continuous robotics domains. This approach builds on the…
We investigate the feasibility of deploying Deep-Q based deep reinforcement learning agents to job-shop scheduling problems in the context of modular production facilities, using discrete event simulations for the environment. These…
Classical reinforcement learning (RL) aims to optimize the expected cumulative reward. In this work, we consider the RL setting where the goal is to optimize the quantile of the cumulative reward. We parameterize the policy controlling…
Double machine learning is a statistical method for leveraging complex black-box models to construct approximately unbiased treatment effect estimates given observational data with high-dimensional covariates, under the assumption of a…