Related papers: Learning to flock through reinforcement

This paper presents a novel zone-based flocking control approach suitable for dynamic multi-agent systems (MAS). Inspired by Reynolds behavioral rules for $boids$, flocking behavioral rules with the zones of repulsion, conflict, attraction,…

We study the (hydro-)dynamics of multi-species driven by alignment. What distinguishes the different species is the protocol of their interaction with the rest of the crowd: the collective motion is described by different communication…

When biological communities use signaling structures for complex coordination, 'free-riders' emerge. The free-riding agents do not contribute to the community resources (signals), but exploit them. Most models of such 'selfish' behavior…

Smart active particles can acquire some limited knowledge of the fluid environment from simple mechanical cues and exert a control on their preferred steering direction. Their goal is to learn the best way to navigate by exploiting the…

Collective behavior occurs ubiquitously in nature and it plays a key role in bacterial colonies, mammalian cells or flocks of birds. Here, we examine the average density and velocity of self-propelled particles, which are described by a…

We consider the problem of understanding the coordinated movements of biological or artificial swarms. In this regard, we propose a learning scheme to estimate the coordination laws of the interacting agents from observations of the swarm's…

Standard computer vision systems assume access to intelligently captured inputs (e.g., photos from a human photographer), yet autonomously capturing good observations is a major challenge in itself. We address the problem of learning to…

The subject of this paper is reinforcement learning. Policies are considered here that produce actions based on states and random elements autocorrelated in subsequent time instants. Consequently, an agent learns from experiments that are…

We present a general framework for modeling a wide selection of flocking scenarios under free boundary conditions. Several variants have been considered - including examples for the widely observed behavior of hierarchically interacting…

We generalize the Vicsek model to describe the collective behaviour of polar circle swimmers with local alignment interactions. While the phase transition leading to collective motion in 2D (flocking) occurs at the same interaction to noise…

Introducing environmental feedback into evolutionary game theory has led to the development of eco-evolutionary games, which have gained popularity due to their ability to capture the intricate interplay between the environment and…

Several models of flocking have been promoted based on simulations with qualitatively naturalistic behavior. In this paper we provide the first direct application of computational modeling methods to infer flocking behavior from…

A major problem in evolutionary biology is how species learn and adapt under the constraint of environmental conditions and competition of other species. Models of cyclic dominance provide simplified settings in which such questions can be…

Social dilemmas have been widely studied to explain how humans are able to cooperate in society. Considerable effort has been invested in designing artificial agents for social dilemmas that incorporate explicit agent motivations that are…

The reinforcement learning paradigm allows, in principle, for complex behaviours to be learned directly from simple reward signals. In practice, however, it is common to carefully hand-design the reward function to encourage a particular…

Flocking is a fascinating phenomenon observed across a wide range of living organisms. We investigate, based on a simple self-propelled particle model, how the emergence of ordered motion in a collectively moving group is influenced by the…

Reinforcement Learning (RL) is an emerging approach to control many dynamical systems for which classical control approaches are not applicable or insufficient. However, the resultant policies may not generalize to variations in the…

We study the emergence of cooperative behaviors in reinforcement learning agents by introducing a challenging competitive multi-agent soccer environment with continuous simulated physics. We demonstrate that decentralized, population-based…

Collective human knowledge has clearly benefited from the fact that innovations by individuals are taught to others through communication. Similar to human social groups, agents in distributed learning systems would likely benefit from…

Peer learning is a novel high-level reinforcement learning framework for agents learning in groups. While standard reinforcement learning trains an individual agent in trial-and-error fashion, all on its own, peer learning addresses a…