6 papers
Dreamer-CPC: Message Learning with World Models for Decentralized Multi-agent Reinforcement Learning
Taisuke Takayama, Naoto Yoshida, Tadahiro Taniguchi
In multi-agent reinforcement learning (MARL), inter-agent communication is effective for improving performance under partial observability. Representation learning-based approaches…
Linking Homeostasis to Reinforcement Learning: Internal State Control of Motivated Behavior
Naoto Yoshida, Henning Sprekeler, Boris Gutkin
For living beings, survival depends on effective regulation of internal physiological states through motivated behaviors. In this perspective we propose that Homeostatically Regula…
Homeostatic Coupling for Prosocial Behavior
Naoto Yoshida, Kingson Man
When regarding the suffering of others, we often experience personal distress and feel compelled to help\footnote{Preprint. Under review.}. Inspired by living systems, we investiga…
Reward-Independent Messaging for Decentralized Multi-Agent Reinforcement Learning
Naoto Yoshida, Tadahiro Taniguchi
In multi-agent reinforcement learning (MARL), effective communication improves agent performance, particularly under partial observability. We propose MARL-CPC, a framework that en…
Emergence of Implicit World Models from Mortal Agents
Kazuya Horibe, Naoto Yoshida
We discuss the possibility of world models and active exploration as emergent properties of open-ended behavior optimization in autonomous agents. In discussing the source of the o…
Empathic Coupling of Homeostatic States for Intrinsic Prosociality
Naoto Yoshida, Kingson Man
When regarding the suffering of others, we often experience personal distress and feel compelled to help. Inspired by living systems, we investigate the emergence of prosocial beha…