paper-with-me

Papers

Few is More: Task-Efficient Skill-Discovery for Multi-Task Offline Multi-Agent Reinforcement Learning

2025-02-13 · Xun Wang, Zhuoran Li, Hai Zhong, Longbo Huang

As a data-driven approach, offline MARL learns superior policies solely from offline datasets, ideal for domains rich in historical data but with high interaction costs and risks. However, most existing methods are task-specific, requiring retraining for new tasks, leading to redundancy and inefficiency. To address this issue, in this paper, we propose a task-efficient multi-task offline MARL algorithm, Skill-Discovery Conservative Q-Learning (SD-CQL). Unlike existing offline skill-discovery methods, SD-CQL discovers skills by reconstructing the next observation. It then evaluates fixed and variable actions separately and employs behavior-regularized conservative Q-learning to execute the optimal action for each skill. This approach eliminates the need for local-global alignment and enables strong multi-task generalization from limited small-scale source tasks. Substantial experiments on StarCraftII demonstrates the superior generalization performance and task-efficiency of SD-CQL. It achieves the best performance on $\textbf{10}$ out of $14$ task sets, with up to $\textbf{65%}$ improvement on individual task sets, and is within $4\%$ of the best baseline on the remaining four.

📄 PDF Abstract BibTeX arXiv:2502.08985

Code (0)

등록된 구현이 없습니다.

Tasks

Learning to ExecuteMulti-agent Reinforcement LearningQ-Learning

Methods 이 논문이 사용한 방법론

Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…

Similar Papers 제목 키워드 기반

MRSD: Multi-Resolution Skill Discovery for HRL Agents

2025-05-27 · Shashank Sharma, Janina Hoffmann, Vinay Namboodiri

Hierarchical reinforcement learning (HRL) relies on abstract skills to solve long-horizon tasks efficiently. While existing skill discovery methods learns these skills automatically, they are limited to a single skill pe…

Hierarchical Reinforcement Learning

Skill Transfer and Discovery for Sim-to-Real Learning: A Representation-Based Viewpoint

2024-04-07 · Haitong Ma, Zhaolin Ren, Bo Dai, Na Li

We study sim-to-real skill transfer and discovery in the context of robotics control using representation learning. We draw inspiration from spectral decomposition of Markov decision processes. The spectral decomposition…

Representation Learning

Lipschitz-constrained Unsupervised Skill Discovery

2022-02-02 · ICLR 2022 4 · Seohong Park, Jongwook Choi, Jaekyeom Kim, Honglak Lee 외

We study the problem of unsupervised skill discovery, whose goal is to learn a set of diverse and useful skills with no external reward. There have been a number of skill discovery methods based on maximizing the mutual …

DiversityMuJoCo

Hierarchical Multi-Agent Skill Discovery

2023-09-21 · NeurIPS 2023 11

Skill discovery has shown significant progress in unsupervised reinforcement learning. This approach enables the discovery of a wide range of skills without any extrinsic reward, which can be effectively combined to tack…

Unsupervised Skill Discovery with Bottleneck Option Learning

2021-06-27 · Jaekyeom Kim, Seohong Park, Gunhee Kim

Having the ability to acquire inherent skills from environments without any external rewards or supervision like humans is an important problem. We propose a novel unsupervised skill discovery method named Information Bo…

DisentanglementMuJoCo