Replication of Multi-agent Reinforcement Learning for the "Hide and Seek" Problem

TL;DR

This paper replicates multi-agent reinforcement learning for the 'Hide and Seek' problem, introducing enhanced agent mobility and strategies, and emphasizes the importance of reproducibility in RL research.

Contribution

It provides a detailed replication of RL strategies in complex environments with improved agent capabilities, addressing reproducibility issues.

Findings

Hider agents developed more efficient strategies with fewer training steps.

Enhanced mobility led to more complex and effective hiding and seeking behaviors.

Reproducibility challenges in RL are highlighted and addressed.

Abstract

Reinforcement learning generates policies based on reward functions and hyperparameters. Slight changes in these can significantly affect results. The lack of documentation and reproducibility in Reinforcement learning research makes it difficult to replicate once-deduced strategies. While previous research has identified strategies using grounded maneuvers, there is limited work in more complex environments. The agents in this study are simulated similarly to Open Al's hider and seek agents, in addition to a flying mechanism, enhancing their mobility, and expanding their range of possible actions and strategies. This added functionality improves the Hider agents to develop a chasing strategy from approximately 2 million steps to 1.6 million steps and hiders