Lux AI Season 3: Multi-Agent Meta Learning at Scale

Stone Tao, Akarsh Kumar, Bovard Doerschuk-Tiberi, Isabelle Pan, Addison Howard, Hao Su

Keywords: Environment Design, Multi-Agent Reinforcement Learning, Meta Learning

TL;DR: Testing adaptability of agents via a 5-game sequence with variable game dynamics and partial observability. Competition can result in dataset of rule-based agents providing diverse, high-quality gameplay data for analysis against learned agents.

Abstract: The proposed competition revolves around testing the limits of agents (e.g rule-based or Meta RL agents) when it comes to adapting to a game with changing dynamics. We propose a unique 1v1 competition format where both teams face off in a sequence of 5 games. The game mechanics, along with partial observability are designed to ensure that optimal gameplay requires agents to efficiently explore and discover the game dynamics. They ensure that the strongest agents may play "suboptimally" in game 1 to explore, but then win easily in games 2 to 5 by leveraging information gained through game 1 and adapting. This competition provides a GPU parallelized game environment via jax to enable fast training/evaluation on a single GPU, lowering barriers of entry to typically industry-level scales of research. Participants can submit their agents to compete against other submitted agents on a online leaderboard hosted by Kaggle ranked by a Trueskill ranking system. The results of the competition will provide a dataset of top open-sourced rule-based agents as well as many game episodes that can lead to unique analysis (e.g. quantifying emergence/surprise) past competitions cannot usually provide thanks to the number of competitors the Lux AI Challenges often garner.

Competition Timeline:

July 1st to July 24th - Beta testing period where participants may compete for non-monetary prizes and help test the game. Game mechanics and UI/UX designs will change to reflect feedback and better balance the game / make it more interesting to increasing participation

July 24th to October 18th: Main competition starts. All game rules/designs will be fixed and unchanged.

October 18th to October 31st: Submissions are due October 18th and final submissions are evaluated until October 31st to determine final rankings.

Website: https://lux-ai.org/

Primary Contact Email: [e-mail]

Participant Contact Email: [e-mail]

Workshop Format: Hybrid (Vancouver + some online speakers)

Preferred Timezone: PST

Submission Number: 42