Peer-Aware Cost Estimation in Nonlinear General-Sum Dynamic Games for Mutual Learning and Intent Inference
Human-robot interactions can be modeled as incomplete-information general-sum dynamic games since the objective functions of both agents are not explicitly known to each other. However, solving for equilibrium policies for such games presents a major challenge, especially if the games involve nonlinear underlying dynamics. To simplify the problem, existing work often assumes that one agent is an expert with complete information about its peer, which can lead to biased estimates and failures in coordination. To address this challenge, we propose a nonlinear peer-aware cost estimation (N-PACE) algorithm for general-sum dynamic games. In N-PACE, using iterative linear quadratic (LQ) approximation of the nonlinear general-sum game, each agent explicitly models the learning dynamics of its peer agent while inferring their objective functions, leading to unbiased fast learning in inferring the unknown objective function of the peer agent, which is critical for task completion and safety assurance. Additionally, we demonstrate how N-PACE enables \textbf{intent communication} in such multi-agent systems by explicitly modeling the peer's learning dynamics.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
PACE: A Framework for Learning and Control in Linear Incomplete-Information Differential Games
In this paper, we address the problem of a two-player linear quadratic differential game with incomplete information, a scenario commonly encountered in multi-agent control, human-robot interaction (HRI), and approximati…
parameter estimationStudy of Energy-Efficient Distributed RLS-based Learning with Coarsely Quantized Signals
In this work, we present an energy-efficient distributed learning framework using coarsely quantized signals for Internet of Things (IoT) networks. In particular, we develop a distributed quantization-aware recursive lea…
parameter estimationQuantizationCausality-based Cost Allocation for Peer-to-Peer Energy Trading in Distribution System
While peer-to-peer energy trading has the potential to harness the capabilities of small-scale energy resources, a peer-matching process often overlooks power grid conditions, yielding increased losses, line congestion, …
energy tradingEnergy-Efficient Distributed Learning Algorithms for Coarsely Quantized Signals
In this work, we present an energy-efficient distributed learning framework using low-resolution ADCs and coarsely quantized signals for Internet of Things (IoT) networks. In particular, we develop a distributed quantiza…
parameter estimationQuantizationEstimation Network Design framework for efficient distributed optimization
Distributed decision problems features a group of agents that can only communicate over a peer-to-peer network, without a central memory. In applications such as network control and data ranking, each agent is only affec…
Distributed Optimization