Battlesnake Challenge: A Multi-agent Reinforcement Learning Playground with Human-in-the-loop — mentioned by ArtWomb

Thu, 30 Jul 2020 11:50:44 GMT

The power of community multi-agent simulations lie in participatory environments. Every geospatially dispersed team shares their collected data and eventually this is how the world gets solved. I wish I had more time to participate! I noticed an interesting Human-in-the-Loop Learning (HILL) challenge running BattleSnake with AWS SageMaker. It's a well-known, time-tested result. Agents + Humans consistently outperform either humans or agents alone ;) Battlesnake Challenge: A Multi-agent Reinforcement Learning Playground with Human-in-the-loop https://arxiv.org/abs/2007.10504

Paper and discussion history. A mention is not an endorsement.

Battlesnake Challenge: A Multi-agent Reinforcement Learning Playground with Human-in-the-loop · HackerPapers discussions

Battlesnake Challenge: A Multi-agent Reinforcement Learning Playground with Human-in-the-loop — mentioned by ArtWomb