paper-with-me

홈 › Papers

Towards Sample Efficient Agents through Algorithmic Alignment

2020-08-07 · Mingxuan Li, Michael L. Littman

In this work, we propose and explore Deep Graph Value Network (DeepGV) as a promising method to work around sample complexity in deep reinforcement-learning agents using a message-passing mechanism. The main idea is that the agent should be guided by structured non-neural-network algorithms like dynamic programming. According to recent advances in algorithmic alignment, neural networks with structured computation procedures can be trained efficiently. We demonstrate the potential of graph neural network in supporting sample efficient learning by showing that Deep Graph Value Network can outperform unstructured baselines by a large margin in solving the Markov Decision Process (MDP). We believe this would open up a new avenue for structured agent design. See https://github.com/drmeerkat/Deep-Graph-Value-Network for the code.

📄 PDF Abstract BibTeX arXiv:2008.03229

Code (1)

drmeerkat/Deep-Graph-Value-Network 공식 구현 pytorch

Tasks

Deep Reinforcement LearningGraph Neural NetworkReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Graph Neural Network 설명 없음

Similar Papers 제목 키워드 기반

Beyond Human Intervention: Algorithmic Collusion through Multi-Agent Learning Strategies

2025-01-28 · Suzie Grondin, Arthur Charpentier, Philipp Ratz

Collusion in market pricing is a concept associated with human actions to raise market prices through artificially limited supply. Recently, the idea of algorithmic collusion was put forward, where the human action in th…

Commodities Trading through Deep Policy Gradient Methods

2023-08-10 · Jonas Hanetho

Algorithmic trading has gained attention due to its potential for generating superior returns. This paper investigates the effectiveness of deep reinforcement learning (DRL) methods in algorithmic commodities trading. It…

Algorithmic TradingDeep Reinforcement LearningPolicy Gradient MethodsTime Series

Socially-Weighted Alignment: A Game-Theoretic Framework for Multi-Agent LLM Systems

2026-02-16 · Furkan Mumcu, Yasin Yilmaz arxiv

Deploying large language model (LLM) agents in shared environments introduces a fundamental tension between individual alignment and collective stability: locally rational decisions can impose negative externalities that…

Multi-agent Reinforcement LearningDecision Making

Teaming Up with AI: Coordination and Cooperation

2026-07-03 · Nicole Immorlica, Inbal Talgam-Cohen arxiv

Successful diffusion of AI in the workforce hinges on the economic value that AI brings to human endeavors. Bringing AI into the workforce is more than deploying a powerful new technology -- it is launching a new form of…

Impact of Price Inflation on Algorithmic Collusion Through Reinforcement Learning Agents

2025-04-05 · Sebastián Tinoco, Andrés Abeliuk, Javier Ruiz del Solar

Algorithmic pricing is increasingly shaping market competition, raising concerns about its potential to compromise competitive dynamics. While prior work has shown that reinforcement learning (RL)-based pricing algorithm…

Reinforcement Learning (RL)