Offline Pre-trained Multi-agent Decision Transformer: One Big Sequence Model Tackles All SMAC Tasks

Abstract

Offline reinforcement learning leverages previously-collected offline datasets to learn optimal policies with no necessity to access the real environment. Such a paradigm is also desirable for multi-agent reinforcement learning (MARL) tasks, given the increased interactions among agents and with the enviroment. Yet, in MARL, the paradigm of offline pre-training with online fine-tuning has not been studied, nor datasets or benchmarks for offline MARL research are available. In this paper, we facilitate the research by providing large-scale datasets, and use them to examine the usage of the Decision Transformer in the context of MARL. We investigate the generalisation of MARL offline pre-training in the following three aspects: 1) between single agents and multiple agents, 2) from offline pretraining to the online fine-tuning, and 3) to that of multiple downstream tasks with few-shot and zero-shot capabilities. We start by introducing the first offline MARL dataset with diverse quality l

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keymeng2021offline

Related papers

• Self-confirming Transformer For Belief-conditioned Adaptation In Offline Multi-agent Reinforcement Learning (2023)0.00
• Off-the-grid MARL: Datasets With Baselines For Offline Multi-agent Reinforcement Learning (2023)2.26
• Solving Continual Offline Reinforcement Learning With Decision Transformer (2024)0.00
• Harmodt: Harmony Multi-task Decision Transformer For Offline Reinforcement Learning (2024)0.00
• Representation Matters: Offline Pretraining For Sequential Decision Making (2021)0.00
• When Should We Prefer Decision Transformers For Offline Reinforcement Learning? (2023)0.00
• DLM: Unified Decision Language Models For Offline Multi-agent Sequential Decision Making (2026)0.00
• Decision Mamba: A Multi-grained State Space Model With Self-evolution Regularization For Offline RL (2024)0.00