REVIEW 6 cited by
Graph Convolutional Reinforcement Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Learning to cooperate is crucially important in multi-agent environments. The key is to understand the mutual interplay between agents. However, multi-agent environments are highly dynamic, where agents keep moving and their neighbors change quickly. This makes it hard to learn abstract representations of mutual interplay between agents. To tackle these difficulties, we propose graph convolutional reinforcement learning, where graph convolution adapts to the dynamics of the underlying graph of the multi-agent environment, and relation kernels capture the interplay between agents by their relation representations. Latent features produced by convolutional layers from gradually increased receptive fields are exploited to learn cooperation, and cooperation is further improved by temporal relation regularization for consistency. Empirically, we show that our method substantially outperforms existing methods in a variety of cooperative scenarios.
Forward citations
Cited by 6 Pith papers
-
Federated Physics-Grounded Reinforcement Learning for Distributed Stability Control in Smart Grids
On IEEE 39-bus simulations, federated multi-agent PPO with physics-grounded neighbor observations stabilizes all tested faults 72% faster and with 7–14× less control power than centralized feedback linearization, with...
-
TrajAware: Graph Cross-Attention and Trajectory-Aware for Generalisable VANETs under Partial Observations
TrajAware combines action-space pruning, graph cross-attention, and trajectory prediction to achieve near-shortest-path routing in VANETs under partial observations, evaluated across unseen simulated cities.
-
Graph World Model
The Graph World Model uses action nodes and graph message passing to unify multimodal and graph-structured tasks, but its 'outperforms or matches' claim is contradicted by results on Goodreads.
-
Toward Adaptable Multi-Agent Reinforcement Learning: An Assumption-Aware Review
A survey proposing adaptability as a three-part taxonomy (learning, policy, scenario-driven) for organizing and evaluating MARL under changing conditions.
-
General Autonomous Cybersecurity Defense: Learning Robust Policies for Dynamic Topologies and Diverse Attackers
A graph-neural-network plus optimal-transport agent trained on procedurally generated networks generalizes across topology changes and two attacker types in the CAGE 2 simulation.
-
Feedback Attribution and Representation Geometry: Metrics for Comparing Individual and Shared Rewards in MARL
On SMACv2, role geometry in shared-encoder MARL is set by whether unit type is observed, not by individual vs shared reward; reward attribution affects behavior, mainly action diversity.
Discussion (0). Sign in to comment.