English

Adaptive Episode Length Adjustment for Multi-agent Reinforcement Learning

Multiagent Systems 2025-05-27 v1

Abstract

In standard reinforcement learning, an episode is defined as a sequence of interactions between agents and the environment, which terminates upon reaching a terminal state or a pre-defined episode length. Setting a shorter episode length enables the generation of multiple episodes with the same number of data samples, thereby facilitating an exploration of diverse states. While shorter episodes may limit the collection of long-term interactions, they may offer significant advantages when properly managed. For example, trajectory truncation in single-agent reinforcement learning has shown how the benefits of shorter episodes can be leveraged despite the trade-off of reduced long-term interaction experiences. However, this approach remains underexplored in MARL. This paper proposes a novel MARL approach, Adaptive Episode Length Adjustment (AELA), where the episode length is initially limited and gradually increased based on an entropy-based assessment of learning progress. By starting with shorter episodes, agents can focus on learning effective strategies for initial states and minimize time spent in dead-end states. The use of entropy as an assessment metric prevents premature convergence to suboptimal policies and ensures balanced training over varying episode lengths. We validate our approach using the StarCraft Multi-agent Challenge (SMAC) and a modified predator-prey environment, demonstrating significant improvements in both convergence speed and overall performance compared to existing methods. To the best of our knowledge, this is the first study to adaptively adjust episode length in MARL based on learning progress.

Keywords

Cite

@article{arxiv.2505.19637,
  title  = {Adaptive Episode Length Adjustment for Multi-agent Reinforcement Learning},
  author = {Byunghyun Yoo and Younghwan Shin and Hyunwoo Kim and Euisok Chung and Jeongmin Yang},
  journal= {arXiv preprint arXiv:2505.19637},
  year   = {2025}
}
R2 v1 2026-07-01T02:38:39.218Z