Constraint Learning in Multi-Agent Dynamic Games from Demonstrations of Local Nash Interactions
We present an inverse dynamic game-based algorithm to learn parametric constraints from a given dataset of local Nash equilibrium interactions between multiple agents. Specifically, we introduce mixed-integer linear programs (MILP) encoding the Karush-Kuhn-Tucker (KKT) conditions of the interacting agents, which recover constraints consistent with the local Nash stationarity of the interaction demonstrations. We establish theoretical guarantees that our method learns inner approximations of the true safe and unsafe sets. We also use the interaction constraints recovered by our method to design motion plans that robustly satisfy the underlying constraints. Across simulations and hardware experiments, our methods accurately inferred constraints and designed safe interactive motion plans for various classes of constraints, both convex and non-convex, from interaction demonstrations of agents with nonlinear dynamics.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Competitive Multi-agent Inverse Reinforcement Learning with Sub-optimal Demonstrations
This paper considers the problem of inverse reinforcement learning in zero-sum stochastic games when expert demonstrations are known to be not optimal. Compared to previous works that decouple agents in the game by assum…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Benchmarking End-to-End Behavioural Cloning on Video Games
Behavioural cloning, where a computer is taught to perform a task based on demonstrations, has been successfully applied to various video games and robotics tasks, with and without reinforcement learning. This also inclu…
Behavioural cloningBenchmarkingReinforcement LearningPolicy Gradient with Self-Attention for Model-Free Distributed Nonlinear Multi-Agent Games
Multi-agent games in dynamic nonlinear settings are challenging due to the time-varying interactions among the agents and the non-stationarity of the (potential) Nash equilibria. In this paper we consider model-free game…
Adversarial Inverse Reinforcement Learning for Mean Field Games
Mean field games (MFGs) provide a mathematically tractable framework for modelling large-scale multi-agent systems by leveraging mean field theory to simplify interactions among agents. It enables applying inverse reinfo…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Stability Certificates for Receding Horizon Games
Game-theoretic MPC (or Receding Horizon Games) is an emerging control methodology for multi-agent systems that generates control actions by solving a dynamic game with coupling constraints in a receding-horizon fashion. …
Autonomous DrivingDecision Makingvalid