Agent Benchmark

Agent benchmarking focuses on evaluating the performance of artificial intelligence agents across diverse tasks and environments, aiming to objectively assess their capabilities and identify areas for improvement. Current research emphasizes developing comprehensive benchmarks that incorporate multiple modalities (e.g., image, text, dialogue), cross-environment compatibility, and nuanced evaluation metrics beyond simple accuracy, often employing techniques like multi-agent reinforcement learning, large language models, and hypergraph convolutions to model agent interactions and decision-making. These advancements are crucial for advancing the field of AI, enabling the development of more robust, reliable, and ethically sound agents for real-world applications ranging from healthcare to aerospace.

Papers

March 7, 2022

Influencing Long-Term Behavior in Multiagent Reinforcement Learning
Dong-Ki Kim, Matthew Riemer, Miao Liu, Jakob N. Foerster, Michael Everett, Chuangchuang Sun, Gerald Tesauro, Jonathan P. How
BEHAVIOR Explanation Agent Benchmark Equilibrium Selection

December 23, 2021

Local Advantage Networks for Cooperative Multi-Agent Reinforcement Learning
Raphaël Avalos, Mathieu Reymond, Ann Nowé, Diederik M. Roijers
Cooperative Multi Agent Reinforcement Learning Agent Benchmark Independent Q Learning Local Network

December 9, 2021

Cooperative Multi-Agent Reinforcement Learning with Hypergraph Convolution
Yunpeng Bai, Chen Gong, Bin Zhang, Guoliang Fan, Xinwen Hou, Yu Liu
Multi Agent System Agent System Cooperative Multi Agent Reinforcement Learning Agent Benchmark Lazy Agent Hypergraph Convolution

Agent Benchmark

Papers

Influencing Long-Term Behavior in Multiagent Reinforcement Learning

Local Advantage Networks for Cooperative Multi-Agent Reinforcement Learning

Cooperative Multi-Agent Reinforcement Learning with Hypergraph Convolution