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

2023-10-09 · Haider Kamal, Muaz A. Niazi, Hammad Afzal

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

📄 PDF Abstract BibTeX arXiv:2310.05430

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning

Emergent Tool Use From Multi-Agent Autocurricula

2019-09-17 · ICLR 2020 1 · Bowen Baker, Ingmar Kanitscheider, Todor Markov, Yi Wu 외

Through multi-agent competition, the simple objective of hide-and-seek, and standard reinforcement learning algorithms at scale, we find that agents create a self-supervised autocurriculum inducing multiple distinct roun…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

AutoDIME: Automatic Design of Interesting Multi-Agent Environments

2022-03-04 · Ingmar Kanitscheider, Harri Edwards

Designing a distribution of environments in which RL agents can learn interesting and useful skills is a challenging and poorly understood task, for multi-agent environments the difficulties are only exacerbated. One app…

Diagnostic MuJoCo Value prediction

Visual Hide and Seek

2019-10-15 · Boyuan Chen, Shuran Song, Hod Lipson, Carl Vondrick

We train embodied agents to play Visual Hide and Seek where a prey must navigate in a simulated environment in order to avoid capture from a predator. We place a variety of obstacles in the environment for the prey to hi…

Navigate

CCL: Collaborative Curriculum Learning for Sparse-Reward Multi-Agent Reinforcement Learning via Co-evolutionary Task Evolution

2025-05-08 · Yufei Lin, Chengwei Ye, Huanzhen Zhang, Kangsheng Wang 외

Sparse reward environments pose significant challenges in reinforcement learning, especially within multi-agent systems (MAS) where feedback is delayed and shared across agents, leading to suboptimal learning. We propose…

Multi-agent Reinforcement Learning

A High-Throughput Compute-Efficient POMDP Hide-And-Seek-Engine (HASE) for Multi-Agent Operations

2026-04-29 · Timothy Flavin, Sandip Sen arxiv

Reinforcement Learning (RL) algorithms exhibit high sample complexity, particularly when applied to Decentralized Partially Observable Markov Decision Processes (Dec-POMDPs). As a response, projects such as SampleFactory…

Reinforcement Learning