arXiv research

Quantum machine learning offers advantages for broader learning tasks.

This paper improves Q-learning bounds using reference-advantage decomposition.

UCB-Advantage learns MDPs with $O(\sqrt{H^2SAT})$ regret.

Study compares adaptive vs fixed query learning methods.

Quantum effects are known to provide an advantage in particle transfer across networks. In order to achieve this advantage, requirements on both a graph type and a quantum system coherence must be found. Here we show that the process of finding these requirements can be automated by learning from simulated examples. Th…

Gradient descent benefits from tangent kernel advantages under specific conditions.

New method learns time-varying home field advantage in football.

Study on when RLVR can learn compositional problems.

Paper proposes FedQ-Advantage for federated Q-learning with near-optimal regret and low communication cost.

The paper tackles scalarization issues in A2C RL algorithms, proposing methods to avoid gradient overlap and noise.

This study improves quantum classifiers by optimizing data preprocessing.

Quantum circuits reveal pathways to dequantization in machine learning models.

Hybrid quantum-classical RL model solves standard benchmark tasks and proves quantum advantage.

Approximate dynamic programming algorithms, such as approximate value iteration, have been successfully applied to many complex reinforcement learning tasks, and a better approximate dynamic programming algorithm is expected to further extend the applicability of reinforcement learning to various tasks. In this paper w…

DG separates successes and failures by gating updates with advantage and surprisal.

Two new criteria help understand the advantage of deep neural networks.

Improved SAC with AWMP for better control tasks.

In the past decade, the field of quantum machine learning has drawn significant attention due to the prospect of bringing genuine computational advantages to now widespread algorithmic methods. However, not all domains of machine learning have benefited equally from quantum enhancements. Notably, deep learning and rein…

Quantum networks offer exponential communication savings for large machine learning models.

One question central to Reinforcement Learning is how to learn a feature representation that supports algorithm scaling and re-use of learned information from different tasks. Successor Features approach this problem by learning a feature representation that satisfies a temporal constraint. We present an implementation…

DRL agents perform poorly at high decision frequencies, but a new algorithm improves performance.

Convolutional networks outperform fully-connected ones in certain tasks.

Quantum ML promises faster data analysis but faces trainability challenges.

New algorithm learns value and advantage functions for continuous-time Markov processes without structural assumptions.

Conditional meta-learning improves meta-learning performance in diverse task environments.

Quantum walks are at the heart of modern quantum technologies. They allow to deal with quantum transport phenomena and are an advanced tool for constructing novel quantum algorithms. Quantum walks on graphs are fundamentally different from classical random walks analogs, in particular, they walk faster than classical o…

Policy gradient is an efficient technique for improving a policy in a reinforcement learning setting. However, vanilla online variants are on-policy only and not able to take advantage of off-policy data. In this paper we describe a new technique that combines policy gradient with off-policy Q-learning, drawing experie…

Quantum correlations enhance generative models, providing a new resource for machine learning.

Develops a method to efficiently use offline data for RL policy optimization.

Latent-state environments with long horizons, such as those faced by recommender systems, pose significant challenges for reinforcement learning (RL). In this work, we identify and analyze several key hurdles for RL in such environments, including belief state error and small action advantage. We develop a general prin…

Real-world tasks are often highly structured. Hierarchical reinforcement learning (HRL) has attracted research interest as an approach for leveraging the hierarchical structure of a given task in reinforcement learning (RL). However, identifying the hierarchical policy structure that enhances the performance of RL is n…

The estimation of advantage is crucial for a number of reinforcement learning algorithms, as it directly influences the choices of future paths. In this work, we propose a family of estimates based on the order statistics over the path ensemble, which allows one to flexibly drive the learning process, towards or agains…

Sparse activations in neural networks are hard to exploit but lead to advantages in learning.

Bayesian estimators for causal inference using hierarchical Gaussian Processes.

Paper introduces DTAE to optimize RL algorithms, balancing exploration and exploitation.

New approach optimizes policies in adversarial MDPs using adversarial learning.

Enhances time-series modeling by dropping patches, improving efficiency and adaptability.

A3RL combines online and offline RL with active sampling to improve policy learning.

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 a, the corresponding value is the expected discounted sum of rewards. The optima…

New model learning objective improves continuous control tasks.

MB-DQN uses different backup lengths for improved reinforcement learning.

Network slicing promises to provision diversified services with distinct requirements in one infrastructure. Deep reinforcement learning (e.g., deep $\mathcal{Q}$-learning, DQL) is assumed to be an appropriate algorithm to solve the demand-aware inter-slice resource management issue in network slicing by regarding the …

Entrocraft addresses RL performance saturation in LLMs by customizing entropy curves.

Quantum computing offers energy savings over classical computing.

KGRL uses reinforcement learning with knowledge graphs for better interactive recommendation.

RQMC improves kernel-based learning by reducing deterministic error and offering computational advantages.

TROLL improves RL for LLMs by replacing clipping with a trust region projection.

Deep reinforcement learning is poised to revolutionise the field of AI and represents a step towards building autonomous systems with a higher level understanding of the visual world. Currently, deep learning is enabling reinforcement learning to scale to problems that were previously intractable, such as learning to p…