Adaptive Behavior Cloning Regularization for Stable Offline-to-Online Reinforcement Learning

October 25, 2022 ยท Declared Dead ยท ๐Ÿ› The European Symposium on Artificial Neural Networks

๐Ÿ’€ CAUSE OF DEATH: 404 Not Found
Code link is broken/dead
Authors Yi Zhao, Rinu Boney, Alexander Ilin, Juho Kannala, Joni Pajarinen arXiv ID 2210.13846 Category cs.LG: Machine Learning Cross-listed cs.RO Citations 47 Venue The European Symposium on Artificial Neural Networks Repository https://github.com/zhaoyi11/adaptive_bc} Last Checked 1 month ago
Abstract
Offline reinforcement learning, by learning from a fixed dataset, makes it possible to learn agent behaviors without interacting with the environment. However, depending on the quality of the offline dataset, such pre-trained agents may have limited performance and would further need to be fine-tuned online by interacting with the environment. During online fine-tuning, the performance of the pre-trained agent may collapse quickly due to the sudden distribution shift from offline to online data. While constraints enforced by offline RL methods such as a behaviour cloning loss prevent this to an extent, these constraints also significantly slow down online fine-tuning by forcing the agent to stay close to the behavior policy. We propose to adaptively weigh the behavior cloning loss during online fine-tuning based on the agent's performance and training stability. Moreover, we use a randomized ensemble of Q functions to further increase the sample efficiency of online fine-tuning by performing a large number of learning updates. Experiments show that the proposed method yields state-of-the-art offline-to-online reinforcement learning performance on the popular D4RL benchmark. Code is available: \url{https://github.com/zhaoyi11/adaptive_bc}.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning

Died the same way โ€” ๐Ÿ’€ 404 Not Found