Efficient Cross-Domain Offline Reinforcement Learning with Dynamics- and Value-Aligned Data Filtering

Cross-domain offline reinforcement learning (RL) aims to train a well-performing agent in the target environment, leveraging both a limited target domain dataset and a source domain dataset with (possibly) sufficient data coverage. Due to the underlying dynamics misalignment between source and target domains, naively merging the two datasets may incur inferior performance. Recent advances address this issue by selectively leveraging source domain samples whose dynamics align well with the target domain. However, our work demonstrates that dynamics alignment alone is insufficient, by examining the limitations of prior frameworks and deriving a new target domain sub-optimality bound for the policy learned on the source domain. More importantly, our theory underscores an additional need for $\mathit{\text{value}}\mathit{\text{alignment}}$, i.e., selecting high-quality, high-value samples from the source domain, a critical dimension overlooked by existing works. Motivated by such theoretical insight, we propose $\underset{‾}{\mathbf{\text{D}}}$ynamics- and $\underset{‾}{\mathbf{\text{V}}}$alue-aligned $\underset{‾}{\mathbf{\text{D}}}$ata $\underset{‾}{\mathbf{\text{F}}}$iltering (DVDF) method, a novel unified cross-domain RL framework that selectively incorporates source domain samples exhibiting strong alignment in $\mathit{\text{both}}\mathit{\text{dynamics}}\mathit{\text{and}}\mathit{\text{values}}$. We empirically study a range of dynamics shift scenarios, including kinematic and morphology shifts, and evaluate DVDF on various tasks and datasets, even in the challenging setting where the target domain dataset contains an extremely limited amount of data. Extensive experiments demonstrate that DVDF consistently outperforms strong baselines with significant improvements.