General-Sum Multi-Agent Continuous Inverse Optimal Control
نویسندگان
چکیده
منابع مشابه
Stochastic Optimal Control in Continuous Space-Time Multi-Agent Systems
Recently, a theory for stochastic optimal control in non-linear dynamical systems in continuous space-time has been developed (Kappen, 2005). We apply this theory to collaborative multi-agent systems. The agents evolve according to a given non-linear dynamics with additive Wiener noise. Each agent can control its own dynamics. The goal is to minimize the accumulated joint cost, which consists o...
متن کاملMulti-agent Inverse Reinforcement Learning for Zero-sum Games
In this paper we introduce a Bayesian framework for solving a class of problems termed Multi-agent Inverse Reinforcement Learning (MIRL). Compared to the well-known Inverse Reinforcement Learning (IRL) problem, MIRL is formalized in the context of a stochastic game rather than a Markov decision process (MDP). Games bring two primary challenges: First, the concept of optimality, central to MDPs,...
متن کاملContinuous Inverse Optimal Control with Locally Optimal Examples
Inverse optimal control, also known as inverse reinforcement learning, is the problem of recovering an unknown reward function in a Markov decision process from expert demonstrations of the optimal policy. We introduce a probabilistic inverse optimal control algorithm that scales gracefully with task dimensionality, and is suitable for large, continuous domains where even computing a full polic...
متن کاملCompetitive 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 assuming optimality in expert strategies, we introduce a new objective function that directly pits experts against Nash Equilibrium strategies, and we design an algorithm to solve fo...
متن کاملOptimal Stochastic Control in Continuous Time with Wiener Processes: General Results and Applications to Optimal Wildlife Management
We present a stochastic optimal control approach to wildlife management. The objective value is the present value of hunting and meat, reduced by the present value of the costs of plant damages and traffic accidents caused by the wildlife population. First, general optimal control functions and value functions are derived. Then, numerically specified optimal control functions and value func...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Robotics and Automation Letters
سال: 2021
ISSN: 2377-3766,2377-3774
DOI: 10.1109/lra.2021.3060411