Timezone: »

 
Learning from Sparse Offline Datasets via Conservative Density Estimation
Zhepeng Cen · Zuxin Liu · Zitong Wang · Yihang Yao · Henry Lam · Ding Zhao

@
in New Frontiers in Learning, Control, and Dynamical Systems »
Event URL: https://openreview.net/forum?id=VMqE3svs9o »

Offline reinforcement learning (RL) offers a promising direction for learning policies from pre-collected datasets without requiring further interactions with the environment. However, existing methods struggle to handle out-of-distribution (OOD) extrapolation errors, especially in sparse reward or scarce data settings. In this paper, we propose a novel training algorithm called Conservative Density Estimation (CDE), which addresses this challenge by explicitly imposing constraints on the state-action occupancy stationary distribution. CDE overcomes the limitations of existing approaches, such as the stationary distribution correction method, by addressing the support mismatch issue in marginal importance sampling. Our method achieves state-of-the-art performance on the D4RL benchmark. Notably, CDE consistently outperforms baselines in challenging tasks with sparse rewards or insufficient data, demonstrating the advantages of our approach in addressing the extrapolation error problem in offline RL.

Author Information

Zhepeng Cen (Carnegie Mellon University)
Zuxin Liu (Carnegie Mellon University)
Zitong Wang (Columbia University)
Yihang Yao (Carnegie Mellon University)
Henry Lam (Columbia University)
Ding Zhao (Carnegie Mellon University)

More from the Same Authors