Replication of Multi-agent Reinforcement Learning for the "Hide and Seek" Problem
This work addresses reproducibility issues in reinforcement learning for researchers, but it is incremental as it builds on existing methods with minor enhancements.
The paper tackled the problem of replicating multi-agent reinforcement learning strategies in complex environments by enhancing agent mobility with a flying mechanism, which reduced the steps needed for hider agents to develop a chasing strategy from approximately 2 million to 1.6 million steps.
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