Peer-aware Cost Estimation In Nonlinear General-sum Dynamic Games For Mutual Learning And Intent Inference

Abstract

Dynamic game theory is a powerful tool in modeling multi-agent interactions and human-robot systems. In practice, since the objective functions of both agents may not be explicitly known to each other, these interactions can be modeled as incomplete-information general-sum dynamic games. 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 (ILQ) approximation of dynamic games, each agent explicitly models the learning dynamics of its peer agent while inferring their objective functions and updating its own control policy accordingly in real time, wh

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysoltanian2025peer

Related papers

• PACE: A Framework For Learning And Control In Linear Incomplete-information Differential Games (2025)0.00
• Cost Inference For Feedback Dynamic Games From Noisy Partial State Observations And Incomplete Trajectories (2023)0.00
• Peer Prediction For Learning Agents (2022)0.00
• Generalized Information Gathering Under Dynamics Uncertainty (2026)0.00
• Learning Equilibrium With Estimated Payoffs In Population Games (2024)0.00
• Policy Gradient With Self-attention For Model-free Distributed Nonlinear Multi-agent Games (2025)0.00
• Approximate Feedback Nash Equilibria With Sparse Inter-agent Dependencies (2024)0.00
• Sample-efficient Learning Of Stackelberg Equilibria In General-sum Games (2021)0.00