Sample efficiencyof ESRL is independent of the chosen risk aversion threshold and quality of the behavior policy.

MARL in real scenarios is still challenging due to the same safety and efficiency concerns in single-agent setting, then it is worth conducting investigation for offline RL in multi-agent setting.

We conduct a novel theoretical analysis to demonstrate CODA's

Based on this, we propose a novel approach, Diffusion-DICE, that directly performs this transformation using diffusion models.

Offline reinforcement learning (RL) aims to learn optimal policies from offline datasets, where the parameterization of policies is crucial but often overlooked.

However, existing offline RL methods tend to behave poorly during fine-tuning. In this paper, we study the fine-tuning problem in the context of conservative offline RL methods and we devise an approach for learning an effective initialization from offline data that also enables fast online fine-tuning capabilities.