LJIR: Learning Joint-Action Intrinsic Reward in cooperative multi-agent reinforcement learning
Effective exploration is the key to achieving high returns for reinforcement learning. Agents
must explore jointly in multi-agent systems to find the optimal joint policy. Due to the …
must explore jointly in multi-agent systems to find the optimal joint policy. Due to the …
Reward design for driver repositioning using multi-agent reinforcement learning
A large portion of passenger requests is reportedly unserviced, partially due to vacant for-
hire drivers' cruising behavior during the passenger seeking process. This paper aims to …
hire drivers' cruising behavior during the passenger seeking process. This paper aims to …
Adaptive incentive design with multi-agent meta-gradient reinforcement learning
Critical sectors of human society are progressing toward the adoption of powerful artificial
intelligence (AI) agents, which are trained individually on behalf of self-interested principals …
intelligence (AI) agents, which are trained individually on behalf of self-interested principals …
End-to-end learning and intervention in games
In a social system, the self-interest of agents can be detrimental to the collective good,
sometimes leading to social dilemmas. To resolve such a conflict, a central designer may …
sometimes leading to social dilemmas. To resolve such a conflict, a central designer may …
Partially observable mean field reinforcement learning
Traditional multi-agent reinforcement learning algorithms are not scalable to environments
with more than a few agents, since these algorithms are exponential in the number of …
with more than a few agents, since these algorithms are exponential in the number of …
Learning to share in networked multi-agent reinforcement learning
Y Yi, G Li, Y Wang, Z Lu - Advances in Neural Information …, 2022 - proceedings.neurips.cc
In this paper, we study the problem of networked multi-agent reinforcement learning (MARL),
where a number of agents are deployed as a partially connected network and each interacts …
where a number of agents are deployed as a partially connected network and each interacts …
Mansa: Learning fast and slow in multi-agent systems
DH Mguni, H Chen, T Jafferjee… - International …, 2023 - proceedings.mlr.press
In multi-agent reinforcement learning (MARL), independent learning (IL) often shows
remarkable performance and easily scales with the number of agents. Yet, using IL can be …
remarkable performance and easily scales with the number of agents. Yet, using IL can be …
Learning to mitigate ai collusion on economic platforms
Algorithmic pricing on online e-commerce platforms raises the concern of tacit collusion,
where reinforcement learning algorithms learn to set collusive prices in a decentralized …
where reinforcement learning algorithms learn to set collusive prices in a decentralized …
Inducing equilibria via incentives: Simultaneous design-and-play ensures global convergence
To regulate a social system comprised of self-interested agents, economic incentives are
often required to induce a desirable outcome. This incentive design problem naturally …
often required to induce a desirable outcome. This incentive design problem naturally …
Gamekeeper: Online learning for admission control of networked open multiagent systems
I Bistritz, N Bambos - IEEE Transactions on Automatic Control, 2024 - ieeexplore.ieee.org
We consider open games where players arrive according to a Poisson process with rate and
stay in the game for an exponential random duration with rate. The game evolves in …
stay in the game for an exponential random duration with rate. The game evolves in …