To model intelligent complex systems engineers use the techniques of distributed artificial intelligence and the agent paradigm increasingly However, the problem of decision making by components of a complex system with local, incomplete, uncertain, exchanged or observed in asynchronous manner is often present in agent models. To provide a solution to this problem, studies on quantum cognition introduce quantum properties such as superposition state and entanglement in the decision process. So how to propose quantum agents models that are capable of implementing both quantum properties of superposition state and entanglement? A case study simulating the Takuzu game illustrates our proposed quantum agent model.To model intelligent complex systems engineers use the techniques of distributed artificial intelligence and the agent paradigm increasingly However, the problem of decision making by components of a complex system with local, incomplete, uncertain, exchanged or observed in asynchronous manner is often present in agent models. To provide a solution to this problem, studies on quantum cognition introduce quantum properties such as superposition state and entanglement in the decision process. So how to propose quantum agents models that are capable of implementing both quantum properties of superposition state and entanglement? A case study simulating the Takuzu game illustrates our proposed quantum agent model.

IEEE Symposium Series on Computational Intelligence (SSCI)Dec 1, 20161 citation

Toward intelligent agents on quantum computers

Klusch

Adaptive Agents and Multi-Agents SystemsJan 1, 20040 citations

Q-ARDNS-Multi: A Multi-Agent Quantum Reinforcement Learning Framework with Meta-Cognitive Adaptation for Complex 3D Environments

Umberto Gonçalves de Sousa

This paper presents Q-ARDNS-Multi, an advanced multi-agent quantum reinforcement learning (QRL) framework that extends the ARDNS-FN-Quantum model, where Q-ARDNS-Multi stands for "Quantum Adaptive Reward-Driven Neural Simulator - Multi-Agent". It integrates quantum circuits with RY gates, meta-cognitive adaptation, and multi-agent coordination mechanisms for complex 3D environments. Q-ARDNS-Multi leverages a 2-qubit quantum circuit for action selection, a dual-memory system inspired by human cognition, a shared memory module for agent cooperation, and adaptive exploration strategies modulated by reward variance and intrinsic motivation. Evaluated in a $10 \times 10 \times 3$ GridWorld environment with two agents over 5000 episodes, Q-ARDNS-Multi achieves success rates of 99.6\% and 99.5\% for Agents 0 and 1, respectively, outperforming Multi-Agent Deep Deterministic Policy Gradient (MADDPG) and Soft Actor-Critic (SAC) in terms of success rate, stability, navigation efficiency, and collision avoidance. The framework records mean rewards of $-304.2891 \pm 756.4636$ and $-295.7622 \pm 752.7103$ , averaging 210 steps to goal, demonstrating its robustness in dynamic settings. Comprehensive analyses, including learning curves, reward distributions, statistical tests, and computational efficiency evaluations, highlight the contributions of quantum circuits and meta-cognitive adaptation. By bridging quantum computing, cognitive science, and multi-agent RL, Q-ARDNS-Multi offers a scalable, human-like approach for applications in robotics, autonomous navigation, and decision-making under uncertainty.This paper presents Q-ARDNS-Multi, an advanced multi-agent quantum reinforcement learning (QRL) framework that extends the ARDNS-FN-Quantum model, where Q-ARDNS-Multi stands for "Quantum Adaptive Reward-Driven Neural Simulator - Multi-Agent". It integrates quantum circuits with RY gates, meta-cognitive adaptation, and multi-agent coordination mechanisms for complex 3D environments. Q-ARDNS-Multi leverages a 2-qubit quantum circuit for action selection, a dual-memory system inspired by human cognition, a shared memory module for agent cooperation, and adaptive exploration strategies modulated by reward variance and intrinsic motivation. Evaluated in a $10 \times 10 \times 3$ GridWorld environment with two agents over 5000 episodes, Q-ARDNS-Multi achieves success rates of 99.6\% and 99.5\% for Agents 0 and 1, respectively, outperforming Multi-Agent Deep Deterministic Policy Gradient (MADDPG) and Soft Actor-Critic (SAC) in terms of success rate, stability, navigation efficiency, and collision avoidance. The framework records mean rewards of $-304.2891 \pm 756.4636$ and $-295.7622 \pm 752.7103$, averaging 210 steps to goal, demonstrating its robustness in dynamic settings. Comprehensive analyses, including learning curves, reward distributions, statistical tests, and computational efficiency evaluations, highlight the contributions of quantum circuits and meta-cognitive adaptation. By bridging quantum computing, cognitive science, and multi-agent RL, Q-ARDNS-Multi offers a scalable, human-like approach for applications in robotics, autonomous navigation, and decision-making under uncertainty.

arXiv:2506.03205Jun 2, 20250 citations

Biological Memories and Agents as Quantum Collectives

Subhash C. Kak

Quantum mechanical models have been proposed for biological processes and for cognition and decision in domains that appear to be beyond the de Broglie wavelength. The basis of such quantum behavior is seen variously as quantum fields and virtual and entangled particles, and the determination that the behavior is quantum is made on coherence, order and interference effects, and non-local behavior. This paper proposes that biological memories and cognitive agents are collectives of quantum objects. Statistical and informational properties of the collectives that need to be taken into consideration are identified. Issues related to mapping of collectives into various energy states and resistance to noise are examined. NeuroQuantology | September 2013 | Volume 11 | Issue 3 | Page 391-398Quantum mechanical models have been proposed for biological processes and for cognition and decision in domains that appear to be beyond the de Broglie wavelength. The basis of such quantum behavior is seen variously as quantum fields and virtual and entangled particles, and the determination that the behavior is quantum is made on coherence, order and interference effects, and non-local behavior. This paper proposes that biological memories and cognitive agents are collectives of quantum objects. Statistical and informational properties of the collectives that need to be taken into consideration are identified. Issues related to mapping of collectives into various energy states and resistance to noise are examined. NeuroQuantology | September 2013 | Volume 11 | Issue 3 | Page 391-398

NeuroQuantologyAug 27, 201315 citations

Quantum Agent Models

Prateek Tandon, Stanley Lam, Ben Shih +3 more

Synthesis lectures on quantum computingJan 1, 20170 citations

10 \times 10 \times 3

GridWorld environment with two agents over 5000 episodes, Q-ARDNS-Multi achieves success rates of 99.6\% and 99.5\% for Agents 0 and 1, respectively, outperforming Multi-Agent Deep Deterministic Policy Gradient (MADDPG) and Soft Actor-Critic (SAC) in terms of success rate, stability, navigation efficiency, and collision avoidance. The framework records mean rewards of

-304.2891 \pm 756.4636

and

-295.7622 \pm 752.7103

, averaging 210 steps to goal, demonstrating its robustness in dynamic settings. Comprehensive analyses, including learning curves, reward distributions, statistical tests, and computational efficiency evaluations, highlight the contributions of quantum circuits and meta-cognitive adaptation. By bridging quantum computing, cognitive science, and multi-agent RL, Q-ARDNS-Multi offers a scalable, human-like approach for applications in robotics, autonomous navigation, and decision-making under uncertainty.