paper-with-me

Papers

Neuron as an Agent

2018-01-01 · ICLR 2018 1 · Shohei Ohsawa, Kei Akuzawa, Tatsuya Matsushima, Gustavo Bezerra, Yusuke Iwasawa, Hiroshi Kajino, Seiya Takenaka, Yutaka Matsuo

Existing multi-agent reinforcement learning (MARL) communication methods have relied on a trusted third party (TTP) to distribute reward to agents, leaving them inapplicable in peer-to-peer environments. This paper proposes reward distribution using {\em Neuron as an Agent} (NaaA) in MARL without a TTP with two key ideas: (i) inter-agent reward distribution and (ii) auction theory. Auction theory is introduced because inter-agent reward distribution is insufficient for optimization. Agents in NaaA maximize their profits (the difference between reward and cost) and, as a theoretical result, the auction mechanism is shown to have agents autonomously evaluate counterfactual returns as the values of other agents. NaaA enables representation trades in peer-to-peer environments, ultimately regarding unit in neural networks as agents. Finally, numerical experiments (a single-agent environment from OpenAI Gym and a multi-agent environment from ViZDoom) confirm that NaaA framework optimization leads to better performance in reinforcement learning.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

counterfactualMulti-agent Reinforcement LearningOpenAI Gymreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

NeuronScope: A Multi-Agent Framework for Explaining Polysemantic Neurons in Language Models

2026-01-07 · Weiqi Liu, Yongliang Miao, Haiyan Zhao, Yanguang Liu 외 arxiv

Neuron-level interpretation in large language models (LLMs) is fundamentally challenged by widespread polysemanticity, where individual neurons respond to multiple distinct semantic concepts. Existing single-pass interpr…

Measure gradients, not activations! Enhancing neuronal activity in deep reinforcement learning

2025-05-29 · Jiashun Liu, Zihao Wu, Johan Obando-Ceron, Pablo Samuel Castro 외

Deep reinforcement learning (RL) agents frequently suffer from neuronal activity loss, which impairs their ability to adapt to new data and learn continually. A common method to quantify and address this issue is the tau…

Deep Reinforcement LearningMuJoCoReinforcement Learning (RL)

RoboNeuron: A Middle-Layer Infrastructure for Agent-Driven Orchestration in Embodied AI

2025-12-11 · Weifan Guan, Qinghao Hu, Huasen Xi, Chenxiao Zhang 외 arxiv

Vision-language-action (VLA) models and LLM agents have advanced rapidly, yet reliable deployment on physical robots is often hindered by an interface mismatch between agent tool APIs and robot middleware. Current implem…

Seeking Next Layer Neurons' Attention for Error-Backpropagation-Like Training in a Multi-Agent Network Framework

2023-10-15 · Arshia Soltani Moakhar, Mohammad Azizmalayeri, Hossein Mirzaei, Mohammad Taghi Manzuri 외

Despite considerable theoretical progress in the training of neural networks viewed as a multi-agent system of neurons, particularly concerning biological plausibility and decentralized training, their applicability to r…

Reinforcement Learning applied to Single Neuron

2015-05-15 · Zhipeng Wang, Mingbo Cai

This paper extends the reinforcement learning ideas into the multi-agents system, which is far more complicated than the previously studied single-agent system. We studied two different multi-agents systems. One is the f…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)