Inverse Reinforcement Learning in Swarm Systems

2016-02-17 · Adrian Šošić, Wasiur R. KhudaBukhsh, Abdelhak M. Zoubir, Heinz Koeppl

Inverse reinforcement learning (IRL) has become a useful tool for learning behavioral models from demonstration data. However, IRL remains mostly unexplored for multi-agent systems. In this paper, we show how the principle of IRL can be extended to homogeneous large-scale problems, inspired by the collective swarming behavior of natural systems. In particular, we make the following contributions to the field: 1) We introduce the swarMDP framework, a sub-class of decentralized partially observable Markov decision processes endowed with a swarm characterization. 2) Exploiting the inherent homogeneity of this framework, we reduce the resulting multi-agent IRL problem to a single-agent one by proving that the agent-specific value functions in this model coincide. 3) To solve the corresponding control problem, we propose a novel heterogeneous learning scheme that is particularly tailored to the swarm setting. Results on two example systems demonstrate that our framework is able to produce meaningful local reward models from which we can replicate the observed global system dynamics.

📄 PDF Abstract BibTeX arXiv:1602.05450

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Show me what you want: Inverse reinforcement learning to automatically design robot swarms by demonstration

2023-01-17 · Ilyes Gharbi, Jonas Kuckling, David Garzón Ramos, Mauro Birattari

Automatic design is a promising approach to generating control software for robot swarms. So far, automatic design has relied on mission-specific objective functions to specify the desired collective behavior. In this pa…

reinforcement-learning Reinforcement Learning (RL)

The Inverse-Wisdom Law: Architectural Tribalism and the Consensus Paradox in Agentic Swarms

2026-04-30 · Dahlia Shehata, Ming Li arxiv

As AI transitions toward multi-agent systems (MAS) to solve complex workflows, research paradigms operate on the axiomatic assumption that agent collaboration mirrors the "Wisdom of the Crowd". We challenge this assumpti…

SwarmRL: Building the Future of Smart Active Systems

2024-04-25 · Samuel Tovey, Christoph Lohrmann, Tobias Merkt, David Zimmer 외

This work introduces SwarmRL, a Python package designed to study intelligent active particles. SwarmRL provides an easy-to-use interface for developing models to control microscopic colloids using classical control and d…

Deep Reinforcement Learning

Learning particle swarming models from data with Gaussian processes

2021-06-04 · Jinchao Feng, Charles Kulick, Yunxiang Ren, Sui Tang

Interacting particle or agent systems that display a rich variety of swarming behaviours are ubiquitous in science and engineering. A fundamental and challenging goal is to understand the link between individual interact…

Friction Gaussian Processes Uncertainty Quantification

Scalable Task-Driven Robotic Swarm Control via Collision Avoidance and Learning Mean-Field Control

2022-09-15 · Kai Cui, Mengguang Li, Christian Fabian, Heinz Koeppl

In recent years, reinforcement learning and its multi-agent analogue have achieved great success in solving various complex control problems. However, multi-agent reinforcement learning remains challenging both in its th…

Collision Avoidance Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning+1