Papers › Towards Sample Efficient Agents through Algorithmic Alignment

Towards Sample Efficient Agents through Algorithmic Alignment

7 Aug 2020arXiv:2008.03229archive 2025-07-28

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.

PaperPDFCode

Code

drmeerkat/Deep-Graph-Value-Network officialmentioned in papermentioned on GitHubpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Deep Reinforcement LearningGraph Neural NetworkReinforcement Learning (RL)

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Graph Neural Network

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections