COMPETITIONS

Delivery Robot Routing Problems Challenge

Delivery Robot Routing Problems (DRP) Challenge is based on multiple robot delivery scenarios, where the objective is to identify a set of collision-free, optimal paths for multiple robots on real-world maps. Using a virtual platform that mimics real-world delivery scenarios, participants are expected to develop algorithms that facilitate safe, efficient, and cost-effective robot delivery of goods.

Methods for Open Agent Systems Evaluation Initiative (MOASEI)

Welcome to the inaugural MOASEI Competition, bringing together students, researchers, and professionals from around the world interested in addressing the challenges of Open Agent Systems (OASYS)! The first event to provide unique benchmarking to evaluate the effectiveness of Multiagent Reinforcement Learning (MARL) OASYS. What makes MOASEI unique is the focus on OASYS, which is characterized by the ability of agents and/or tasks that can join or leave the system at any time. The competition will feature a series of benchmark domains that capture the key challenges of OASYS, such as robustness and adaptability. Participants will be asked to submit their MARL checkpoints, which will be evaluated on their performance across one or more of these tracks. The competition will be held leading up to and culminating at the AAMAS conference, providing a unique opportunity for participants to showcase their work to the broader multiagent systems community. We look forward to your participation and hope to see you at the competition!

The Third International Maritime Capture the Flag Competition

The Maritime Capture the Flag (MCTF) Competition addresses the problem of multi-agent reinforcement learning (MARL) for playing a multi-player Capture-the-Flag game within a real-time simulation of a maritime gaming environment. Participants are invited to submit software code in Python for three agents that can play the game as a team against an opponent team, while maximizing their team’s score. Example code for training agents to play MCTF using the RLlib MARL library and for testing trained agent policies against baseline opponent strategies are included in the provided code repository.

Evaluating Decision Agents under Non-Stationarity

Welcome to the AAMAS 2026 Non-Stationarity Challenge Page! This competition, co-located with AAMAS 2026, invites researchers and practitioners to develop and evaluate decision-making agents that can effectively adapt to non-stationary environments using the NS-Gym framework. Participants will design agents capable of detecting, adapting to, and recovering from dynamic environmental shifts. The solution method is open to any approach, including but not limited to reinforcement learning, online planning, meta-learning, and continuous learning. The competition aims to foster innovation in adaptive decision-making and provide insights into the challenges of non-stationary environments. Results will be presented at the AAMAS 2026 conference.

Coordination, Organizations, Institutions, Norms and Ethics for Governance of Multi-Agent Systems (COINE)

Planet Wars is a real-time strategy (RTS) game where AI agents compete to gain control of planets and destroy enemy units. The challenge is to develop agents that can play well across a wide range of game parameters and against diverse opponent strategies.

League of Robot Runners 2026 Competition Proposal

The League of Robot Runners, sponsored by Amazon Robotics, is a competition series where participants tackle the core combinatorial challenges found in cooperative multi-robot coordination problems.

For the 2026 season, we are raising the bar. In addition to task assignment and lifelong planning, we are introducing stochasticity and uncertainty management. These challenges mirror high-impact industrial applications—such as warehouse logistics and advanced manufacturing—where robots must adapt to real-world imperfections and delays in real-time.