2 citations · 2 across the 9 of their papers we have counts for
5 papers · 1 filter
SPhyR: Spatial-Physical Reasoning Benchmark on Material Distribution
Philipp D. Siedler
We introduce a novel dataset designed to benchmark the physical and spatial reasoning capabilities of Large Language Models (LLM) based on topology optimization, a method for compu…
Learning to Communicate and Collaborate in a Competitive Multi-Agent Setup to Clean the Ocean from Macroplastics
Philipp Dominic Siedler
Finding a balance between collaboration and competition is crucial for artificial agents in many real-world applications. We investigate this using a Multi-Agent Reinforcement Lear…
Dynamic Collaborative Multi-Agent Reinforcement Learning Communication for Autonomous Drone Reforestation
Philipp Dominic Siedler
We approach autonomous drone-based reforestation with a collaborative multi-agent reinforcement learning (MARL) setup. Agents can communicate as part of a dynamically changing netw…
Collaborative Auto-Curricula Multi-Agent Reinforcement Learning with Graph Neural Network Communication Layer for Open-ended Wildfire-Management Resource Distribution
Philipp Dominic Siedler
Most real-world domains can be formulated as multi-agent (MA) systems. Intentionality sharing agents can solve more complex tasks by collaborating, possibly in less time. True coop…
The Power of Communication in a Distributed Multi-Agent System
Philipp Dominic Siedler
Single-Agent (SA) Reinforcement Learning systems have shown outstanding re-sults on non-stationary problems. However, Multi-Agent Reinforcement Learning(MARL) can surpass SA system…