Public articles linked to the same research event.
arXiv This work proposes a foundation-model-aided, fully decentralized multi-agent reinforcement learning framework in which a self-supervised forward-dynamics foundation model serves as a reward-agnostic critic backbone and devices exchange only scalar rewards via local consensus; it provides a finite-time convergence analysis and reports at least about 55% faster convergence than end-to-end training across fair-AoI, max-sum-rate, and fair-rate random access optimization tasks.
This work proposes a foundation-model-aided, fully decentralized multi-agent reinforcement learning framework in which a self-supervised forward-dynamics foundation model serves as a reward-agnostic critic backbone and devices exchange only scalar rewards via local consensus; it provides a finite-time convergence analysis and reports at least about 55% faster convergence than end-to-end training across fair-AoI, max-sum-rate, and fair-rate random access optimization tasks.
This work proposes a foundation-model-aided, fully decentralized multi-agent reinforcement learning framework in which a self-supervised forward-dynamics foundation model serves as a reward-agnostic critic backbone and devices exchange only scalar rewards via local consensus; it provides a finite-time convergence analysis and reports at least about 55% faster convergence than end-to-end training across fair-AoI, max-sum-rate, and fair-rate random access optimization tasks.
This work proposes a foundation-model-aided, fully decentralized multi-agent reinforcement learning framework in which a self-supervised forward-dynamics foundation model serves as a reward-agnostic critic backbone and devices exchange only scalar rewards via local consensus; it provides a finite-time convergence analysis and reports at least about 55% faster convergence than end-to-end training across fair-AoI, max-sum-rate, and fair-rate random access optimization tasks.