Related papers: Quantum Advantage in Multi Agent Reinforcement Lea…

Resource allocation is an important issue in cognitive radio systems. It can be done by carrying out negotiation among secondary users. However, significant overhead may be incurred by the negotiation since the negotiation needs to be done…

High-quality, large-scale datasets have played a crucial role in the development and success of classical machine learning. Quantum Machine Learning (QML) is a new field that aims to use quantum computers for data analysis, with the hope of…

Classical reinforcement learning (RL) has generated excellent results in different regions; however, its sample inefficiency remains a critical issue. In this paper, we provide concrete numerical evidence that the sample efficiency (the…

The deployment of Unmanned Aerial Vehicle (UAV) swarms as dynamic communication relays is critical for next-generation tactical networks. However, operating in contested environments requires solving a complex trade-off, including…

We consider a coalitional game with the same payoff for all players. To maximize the payoff, the players need to use one collective strategy, if all players are in certain states, and the other strategy otherwise. The current state of each…

The most elementary prepare-and-measure scenarios have no independent measurement inputs. No inputs mean that quantum advantages require two indispensable ingredients: shared entanglement and measurements that can be adapted to the…

Reinforcement learning (RL) is one of the most practical ways to learn from real-life use-cases. Motivated from the cognitive methods used by humans makes it a widely acceptable strategy in the field of artificial intelligence. Most of the…

Quantum Machine Learning (QML) aims to leverage the principles of quantum mechanics to speed up the process of solving machine learning problems or improve the quality of solutions. Among these principles, entanglement with an auxiliary…

Non-stationarity is a fundamental challenge in multi-agent reinforcement learning (MARL), where agents update their behaviour as they learn. Many theoretical advances in MARL avoid the challenge of non-stationarity by coordinating the…

Although multi-agent reinforcement learning can tackle systems of strategically interacting entities, it currently fails in scalability and lacks rigorous convergence guarantees. Crucially, learning in multi-agent systems can become…

In this paper, we generalize to three players the well-known CHSH quantum game. To do so, we consider all possible 3 variables Boolean functions and search among them which ones correspond to a game scenario with a quantum advantage (for a…

We study a general $2 \times 2$ symmetric, entangled, quantum game. When one player has access only to classical strategies while the other can use the full range of quantum strategies, there are ``miracle'' moves available to the quantum…

Quantum algorithms could efficiently solve certain classically intractable problems by exploiting quantum parallelism. To date, whether the quantum entanglement is useful or not for quantum computing is still a question of debate. Here, we…

This paper presents a Quantum Reinforcement Learning (QRL) solution to the dynamic portfolio optimization problem based on Variational Quantum Circuits. The implemented QRL approaches are quantum analogues of the classical…

Combining quantum computing techniques in the form of amplitude amplification with classical reinforcement learning has led to the so-called "hybrid agent for quantum-accessible reinforcement learning", which achieves a quadratic speedup in…

Recent advances in multi-agent reinforcement learning (MARL) have achieved super-human performance in games like Quake 3 and Dota 2. Unfortunately, these techniques require orders-of-magnitude more training rounds than humans and don't…

In this paper we show that, given $k\geq 3$, there exist $k$-player quantum XOR games for which the entangled bias can be arbitrarily larger than the bias of the game when the players are restricted to separable strategies. In particular,…

Centralized value learning is often assumed to improve coordination and stability in multi-agent reinforcement learning, yet this assumption is rarely tested under controlled conditions. We directly evaluate it in a fully tabular…

The application of quantum reinforcement learning (QRL) to real-time control systems faces significant challenges regarding hardware latency, noise susceptibility, and learning convergence. This work presents an end-to-end investigation of…

We present BenchRL-QAS, a unified benchmarking framework for reinforcement learning (RL) in quantum architecture search (QAS) across a spectrum of variational quantum algorithm tasks on 2- to 8-qubit systems. Our study systematically…